# Billing
Source: https://docs.aurinfer.com/Account/billing
View your current plan, manage your subscription via Patreon, and link Discord servers to share your plan benefits.
# Billing
This page shows your current subscription plan and lets you manage it. It also lets you link Discord servers to your account so they share your plan's benefits.
**How to get here:**
> In the left sidebar, click **Account** → then click **Billing**
The full path is: **Account → Billing**
***
## How to Purchase a Plan (Step by Step)
Follow these steps exactly. Don't skip any — especially Step 1, because without it the purchase won't work.
Before you can buy a plan, you **must** link your Patreon account to AurInfer.
**How to do it:**
1. In the left sidebar, click **Account** → then click **Settings**
2. You are now at **Account → Settings**
3. Make sure the **Profile tab** is selected at the top
4. Scroll down to find the **Connected Accounts** section
5. Find the **Patreon** row in the list
6. Click the **Connect** button next to Patreon
7. A Patreon login window will open — log in to your Patreon account
8. Authorize the connection when prompted
9. Once connected, the Patreon row will show a green checkmark or "Connected" status
After Patreon is connected, go back to the left sidebar and click **Account** → **Billing**.
You are now at **Account → Billing**.
On the Billing page, you will see a list of available plans (Spark, Blaze, Aurora, Comet, Eclipse, Galaxy Pass, and Developer plans).
Click on the plan you want to subscribe to.
After clicking a plan, the page will automatically take you to Patreon's checkout page. This is normal — AurInfer handles subscriptions through Patreon.
You'll see the plan name, the price, and a payment form on Patreon.
On the Patreon checkout page:
1. Enter your payment information (credit/debit card or other Patreon-supported methods)
2. Review the charge — confirm it matches the plan you selected
3. Click the "Join" or "Subscribe" button to complete the payment
Once payment goes through, your AurInfer plan upgrades **immediately**. Go back to the AurInfer dashboard and refresh — your new plan limits will be active.
If you already have a Patreon account that's linked, you can skip Step 1 and go straight to Billing to select a plan.
***
## Current Subscription
At the top of the Billing page, your active plan is shown with a clear **Active** badge next to it.
| Field | What it shows |
| ---------------- | ---------------------------------------------------------------------- |
| **Plan Name** | The name of your current subscription tier (e.g., *Aurora*, *Eclipse*) |
| **Price** | Your monthly billing amount |
| **Status Badge** | Shows whether the plan is currently active |
### Managing Your Subscription
AurInfer uses Patreon to handle all subscriptions. On the Billing page you'll find two buttons:
| Button | What it does |
| ----------------------- | ---------------------------------------------------------------------------------------- |
| **Go to FAQs** | Opens the FAQ page with answers to common billing questions |
| **Manage Subscription** | Opens Patreon in a new tab where you can upgrade, downgrade, or cancel your subscription |
**Downgrading your plan:** If you switch to a cheaper plan, the change takes effect at the **start of your next billing cycle** — not immediately. You'll keep your current plan's benefits until then.
***
## Linked Servers
The **Linked Servers** section is where you configure **which Discord server(s) your plan powers**. Every plan — including the free plan and all single-server plans — covers both your account AND a Discord server. You link that server here.
The key difference across plans is simply **how many servers** you can link:
* **Single-server plans** (Free, Spark, Blaze, Aurora) = power 1 Discord server
* **Multi-server plans** (Comet, Eclipse, Galaxy Pass) = power multiple Discord servers simultaneously (2, 5, or 7 servers)
**How it works:** Once you link a server, all members of that server benefit from your plan's limits (voice messages, image generation, higher message counts, etc.). The plan powers both you and the server together.
### How Many Servers You Can Link (by Plan)
| Plan | Server Slots |
| --------------- | ------------ |
| **Free** | 1 server |
| **Spark** | 1 server |
| **Blaze** | 1 server |
| **Aurora** | 1 server |
| **Comet** | 2 servers |
| **Eclipse** | 5 servers |
| **Galaxy Pass** | 7 servers |
### How to Link a Discord Server
**Step 1:** Go to **Account → Billing**
**Step 2:** Scroll down to find the **Linked Servers** section. You'll see how many slots you've used and how many remain (e.g., *"0 / 5 linked, 5 slots remaining"*).
**Step 3:** Click the **Link a server** button. A dropdown or prompt will appear listing Discord servers where your bot is already added.
**Step 4:** Select the server you want to link. Click Confirm.
The server will now appear in your linked servers list and will immediately start sharing your plan's benefits.
Your character's Discord bot **must already be added** to the server before you can link it here. If the server doesn't appear in the list, go invite the bot to that server first (from the Discord integration settings in your character's dashboard), then come back and link it here.
### How to Unlink a Server
Click the server entry in the Linked Servers list and select the unlink option. The server will **immediately** lose access to your plan's features.
Unlinking a server removes its premium access instantly. Any premium features the server was using (higher limits, voice, image generation) will stop working right away until you re-link or the server gets its own subscription.
# Engines
Source: https://docs.aurinfer.com/Account/engines
Set your personal model preferences for AI, voice, and image generation — these override both server and character-level defaults across your entire account.
# Account Engines
This page lets you set your **personal model preferences** that apply across your entire account. Whatever you set here will override the engine settings inside individual characters and individual servers.
**How to get here:**
> In the left sidebar, click **Account** → then click **Engines**
The full path is: **Account → Engines**
Think of it like this: you have engine settings in three places — at the character level, the server level, and the account level. **Account-level settings win.** They have the highest priority and override everything else.
**Priority order (highest to lowest):**
1. **Account Engines** (this page) — overrides everything below
2. **Server Dedicated Engines** (per-server settings in Discord integration) — overrides character defaults
3. **Character AI Engine** (Universal → AI Engine inside each character) — only applies if neither of the above is set
***
## AI Engine
**Full path: Account → Engines → AI Engine section**
This section is at the top of the Engines page. It controls which AI language model (the "brain") all your characters use by default.
### Primary AI Engine
| Setting | What it does |
| -------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
| **Primary AI Engine** (dropdown) | The main AI model used to generate responses for all your characters. Click the dropdown to see available models and select one. |
Next to the dropdown, there may be three icons:
* **Wrench icon** 🔧 — click this to open extra settings for the selected model
* **Info icon** ℹ️ — click this to read about what this model is good at
* **Clear icon** ✕ — click this to reset back to the default model
### Fallback AI Engine
| Setting | What it does |
| --------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Fallback AI Engine** (dropdown) | The backup AI model that activates automatically if the primary engine goes down or returns an error. This keeps your characters online even during model outages. |
Choose a fast, reliable model as your fallback — something lightweight like **Gemma 3n**. It doesn't need to be the most powerful model, just one that is stable and responds quickly so your characters never go fully offline.
***
## Voice Configuration
**Full path: Account → Engines → Voice Configuration section**
This section has two separate settings — one for the voice itself (how it sounds) and one for the AI that decides what to say during voice calls.
### Voice Engine
| Setting | What it does |
| --------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Voice Engine** (dropdown) | The text-to-speech (TTS) model that converts text into spoken audio for your character. This controls what your character sounds like. Example: *Eleven V3* by ElevenLabs. |
### Voice Processing Model
| Setting | What it does |
| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Voice Processing Model** (dropdown) | The AI language model specifically used to **write** what your character says during voice calls. This is separate from the voice synthesis — it decides the content, not the sound. |
Next to each voice processing model option, you'll see its **estimated latency** (e.g., *1.1s*). Pick a model with lower latency for smoother, faster voice conversations.
**Two different settings, two different jobs:**
* **Voice Engine** = controls HOW the character sounds (the voice/audio quality)
* **Voice Processing Model** = controls WHAT the character says during voice calls (the AI writing the words)
Both can be set independently.
***
## Image Generation
**Full path: Account → Engines → Image Generation section**
This section controls which image model is used when any of your characters generates an image.
### Image Engine
| Setting | What it does |
| --------------------------- | -------------------------------------------------------------------------------------------------- |
| **Image Engine** (dropdown) | The AI image generation model used account-wide for all image generation. Example: *Gemini 3 Pro*. |
Select from the available models in the dropdown. This setting applies to all your characters unless you've configured a different model inside a specific character's **Universal → Image Engine** settings — though that character-level setting will be overridden by this account-level setting if both are set.
***
## Configuration Priority — Quick Reference
| Priority | Where the setting lives | Path to get there | Overrides |
| --------------- | ------------------------ | -------------------------------------- | ------------------------ |
| **1 (Highest)** | Account Engines | **Account → Engines** | Everything |
| **2** | Server Dedicated Engines | Server integration settings | Character-level defaults |
| **3 (Lowest)** | Character AI Engine | **Universal → AI Engine → AI Engines** | Nothing (default only) |
Use the Account Engines page to set a consistent baseline that applies to all your characters. Only configure engine settings inside individual characters when you specifically need one character to use a different model than the rest.
# Memory
Source: https://docs.aurinfer.com/Account/memory
View and manage everything your characters remember about you — browse, search, filter, and pin memories across all active characters.
# Account Memory
This page shows you **everything your characters remember about you** from past conversations. Every time a character learns something — your name, a preference, a fact you mentioned — it stores it here as a "memory." You can browse, search, and manage all of those memories from this one page.
**How to get here:**
> In the left sidebar, click **Account** → then click **Memory**
The full path is: **Account → Memory**
This page is different from the **Memory Engine** inside a character's dashboard. That one controls *how* memories work (the settings). This Account Memory page shows *what* has been remembered — the actual stored memories.
***
## Overview Stats
At the very top of the Memory page, two numbers are always visible:
| Stat | What it shows |
| --------------------- | ------------------------------------------------------------------------------- |
| **Total Memories** | How many memory entries exist in total across all your characters |
| **Active Characters** | How many of your characters currently have at least one memory stored about you |
***
## Two Tabs: Browse and Manage Memory
The Memory page has two tabs at the top:
| Tab | What it's for |
| ----------------- | -------------------------------------------------------------------------------------------------- |
| **Browse** | The main view — shows your memory list. This is where you'll spend most of your time. |
| **Manage Memory** | Technical controls for managing memory storage behavior (clearing, resetting, adjusting settings). |
***
## Browse Tab
**Full path: Account → Memory → Browse tab**
### Search & Filters
At the top of the Browse tab, there are tools to help you find specific memories:
| Control | What it does |
| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------- |
| **Search bar** | Type any word or phrase to search through all memory content. For example, type your name to see if the character knows it. |
| **All Characters** (dropdown) | Show memories from all characters, or filter to see only memories from one specific character. |
| **All Types** (dropdown) | Filter by the type of memory (e.g., user facts, preferences, etc.). |
| **Sort** (dropdown) | Sort the list by most recent (default) or other criteria. |
### Memory List
Each entry in the list shows:
| Field | What it shows |
| ------------------ | ------------------------------------------------------------------------------------------------------------ |
| **Character Name** | Which of your characters stored this memory |
| **Timestamp** | When the memory was created (e.g., "about 1 month ago") |
| **Memory Content** | The actual information stored — e.g., "The user's name is Alex" or "The user prefers Python over JavaScript" |
| **Tags** | Labels categorizing the memory — e.g., `user`, `name`, `Working`, `Episodic` |
### Pinning a Memory
Each memory entry has a **pin button**. Click it to pin that memory.
**Why pin a memory?** Pinned memories are treated as high priority — they're less likely to be removed during automatic cleanup. If there's a specific fact you really want your character to always remember about you, pin it.
### Pagination
Memories are shown 20 at a time. Use the **Previous** and **Next** buttons at the bottom of the list to navigate through all pages.
Memories are stored per-character. A memory that Character A has about you is not visible to Character B — each character has its own separate memory of you.
***
## Manage Memory Tab
**Full path: Account → Memory → Manage Memory tab**
This tab has lower-level controls for managing how memory storage works — for when you need to clear out memories or reset memory settings for specific characters.
Any memory deletion done from the Manage Memory tab is **permanent**. Once memories are deleted, the character will not remember the information in future conversations. There is no undo.
# Overview
Source: https://docs.aurinfer.com/Account/overview
A snapshot of your account's activity, usage statistics, and current plan status — all in one place.
# Account Overview
This page is your **account dashboard** — a single page that shows everything happening across your account at a glance. You can see your current plan, how much of your monthly quota you've used, your all-time totals, and a chart of recent activity.
**How to get here:**
> In the left sidebar, click the **Account** section → then click **Overview**
The full path is: **Account → Overview**
***
## Current Plan
At the top of the Overview page, your active subscription plan is shown clearly.
| Field | What it shows |
| ------------- | -------------------------------------------------------------------------------------------------------------------- |
| **Plan Name** | The name of your current subscription (e.g., Free, Spark, Blaze, Aurora, Comet, Eclipse, Galaxy Pass, etc.) |
| **Status** | Whether your plan has usage caps or unlimited usage |
| **Scope** | Confirms the plan applies to your entire account — all your characters and integrations share the same monthly quota |
All your characters share one monthly quota. If you have 3 characters and they all generate images, the image credits are all drawn from the same pool. Your plan covers your whole account, not each character separately.
***
## Monthly Usage
This section shows **how much of your monthly quota you've used** in the current billing period.
| Stat | What it shows |
| ------------------ | --------------------------------------------------------------------- |
| **Voice Messages** | How many voice messages have been generated this month |
| **Images** | How many AI images have been generated this month |
| **Voice Time** | Total minutes of voice call time used this month |
| **Total Messages** | Combined count of all messages sent by all your characters this month |
Below these stats, you'll see the **reset date** — when your monthly usage resets back to zero (e.g., *"Usage resets: August 1"*).
If you're getting close to your monthly limit, you can upgrade your plan from **Account → Billing**. Paid plans have significantly higher or unlimited quotas.
***
## All-Time Stats
Below the monthly section, there's a second set of counters showing your **total usage across all time** — these never reset.
| Stat | What it shows |
| ------------------ | ------------------------------------------------------------------------- |
| **Messages** | Total messages sent by all your characters since your account was created |
| **Voice Messages** | Total voice messages generated across all time |
| **Voice Time** | Total voice call minutes generated across all time |
| **Images** | Total AI images generated across all time |
***
## Activity
At the bottom of the page is a **Daily Activity chart** showing your usage over the last 14 days as a graph.
Use this chart to:
* See which days your characters are most active
* Spot unusually high activity (could mean something unexpected is happening)
* Track whether your character engagement is growing over time
# Settings
Source: https://docs.aurinfer.com/Account/settings
Manage your AurInfer account — update your profile, change your username, manage email addresses, connected accounts, password, active sessions, and delete your account.
# Account Settings
This page manages your **personal AurInfer account** — your profile picture, display name, username, email addresses, connected accounts (like Patreon, Google, Discord), password, active sessions, and account deletion.
**How to get here:**
> In the left sidebar, click **Account** → then click **Settings**
The full path is: **Account → Settings**
This page is split into **two tabs** at the top:
1. **Profile** — your identity and connected accounts
2. **Security** — password and session management
***
## Profile Tab
**Full path: Account → Settings → Profile tab**
This is the first tab you see when you open Account Settings.
### Profile
At the top of the Profile tab:
| Field | What it does |
| ---------- | ----------------------------------------------------------------------------------------- |
| **Avatar** | Your profile picture shown on your account and dashboard. Click it to upload a new image. |
| **Name** | Your display name — shown across the platform to other users. |
After changing the name or avatar, click **Update profile** to save the changes.
### Username
Your username is your unique identifier on AurInfer. It's different from your display name — it's the permanent ID used internally and may appear in your account URL.
Click **Update username** to change it.
Changing your username may break any links or references that use your current username. After changing it, update any shared links you've sent to others.
### Email Addresses
You can have **more than one email address** linked to your account:
| Field | What it does |
| ---------------------- | -------------------------------------------------------------------------------- |
| **Primary Email** | The main email for your account — used for login and notifications. |
| **Secondary Email(s)** | Additional emails you've added. Can be used for alternative login or as backups. |
Click **Add email address** to attach a new email. You can remove secondary emails at any time by clicking the options next to them.
### Connected Accounts
This section shows all **external services connected to your AurInfer account**. These are used for signing in and for platform integrations.
| Service | What it's used for |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Patreon** | **Required for purchasing plans.** This links your Patreon membership to your AurInfer account. You must connect Patreon before you can subscribe to a paid plan. To connect: stay on this page, find the Patreon entry under Connected Accounts, and click **Connect**. |
| **Google** | Allows you to sign in to AurInfer using your Google account. |
| **Discord** | Connects your Discord account for Discord-related features and identity verification. |
Each connected account has an **options menu** (usually a three-dot icon or similar) where you can manage or disconnect the connection.
**To purchase a plan, you must connect Patreon first.** This is done right here: **Account → Settings → Profile tab → Connected Accounts → Patreon → Connect**. Once connected, go to **Account → Billing** to choose and subscribe to a plan.
***
## Security Tab
**Full path: Account → Settings → Security tab**
Click the **Security** tab at the top of the Settings page to switch to this view.
### Password
Update your account password here. Type your new password in the field and click **Update password** to apply.
Use a strong, unique password for your AurInfer account. Your account controls AI characters that may have Discord bot permissions active 24/7 — keeping it secure protects your bots and communities.
### Active Devices
This section lists **every device and browser session that is currently signed in to your account**.
Each session shows:
| Field | What it shows |
| ----------------- | ------------------------------------------------------------------------- |
| **Device Type** | The operating system of the signed-in session — e.g., Windows, Linux, iOS |
| **Browser** | The browser being used — e.g., Chrome, Firefox, Safari |
| **Location** | The approximate geographic location of the session — e.g., Mumbai, India |
| **Session Label** | Whether this entry is your current active session |
To **sign out a device remotely**, click the sign-out button next to that session. This immediately logs out that device — useful if you accidentally left yourself logged in somewhere, or if you see a session you don't recognize.
If you see a session that you don't recognize — different device, unexpected location — sign it out immediately and then change your password.
### Danger Zone
At the very bottom of the Security tab:
| Action | What it does |
| ------------------ | -------------------------------------------------------------------------------------- |
| **Delete account** | Permanently and immediately deletes your entire AurInfer account and everything in it. |
**Deleting your account is permanent and cannot be undone.** Everything will be gone forever: all your characters, integrations (Discord bots, Bluesky accounts, X accounts), memory data, training data, billing connections, and all settings. There is no recovery.
***
## Security Footer
At the bottom of the Settings page, a note confirms that account authentication and session management is handled by **Clerk** — a secure, industry-standard identity platform. Your login credentials are managed through Clerk's infrastructure.
# AI Engine
Source: https://docs.aurinfer.com/Character/ai-engine
Configure the AI models that power your character's responses — primary engine, fallback engine, voice processing model, and advanced settings.
# AI Engine
This is where you choose **which AI brain** your character uses. Different AI models have different personalities, strengths, and speeds. You can also control how the AI writes (through Advanced Settings).
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **AI Engine**
The full path is: **Universal → AI Engine**
This section has **three sub-pages** (shown as tabs or links inside the AI Engine page):
1. **AI Engines** — choose the main AI model
2. **Voice Processing** — choose the AI model used during voice calls
3. **Advanced Settings** — write global instructions and fine-tune how the AI generates text
***
## AI Engines
**Full path: Universal → AI Engine → AI Engines**
This is the first page you see when you open AI Engine. This is where you pick which AI model (the "brain") powers your character's text responses.
### Engine Selection
| Setting | What it does |
| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Selected Engine** (dropdown) | This is the **main AI model** your character uses to write all its replies. Click the dropdown to see all available models and switch to a different one. |
| **Fallback Engine** (dropdown) | This is a **backup AI model**. If the main model is down or broken, the character automatically switches to this one so it keeps responding. Think of it like a backup generator. Defaults to a reliable model like Gemini 2.5 Flash. |
Next to each engine's name you may see small icons that show what it can do — for example, whether it can see images (vision support) or handle very long conversations (extended context).
### Send Multiple Messages
**Send Multiple Messages** is a toggle (on/off switch) on this page.
* **When ON:** Your character can split one reply into multiple short messages sent one after the other — like how a real person sends a quick message, then follows up with another. Makes conversations feel much more natural.
* **When OFF:** The character always sends one single block of text.
### Requesting a Custom Model
If you want a model that isn't listed in the dropdown, scroll to the bottom of the page and click **Request Model** to submit a request to the AurInfer team.
Some of the most powerful models (like GPT-5.6 and other Top-tier models) are only available on Blaze plan and above. If you see a model grayed out with an **Upgrade** button next to it, you need to upgrade your plan to unlock it. You can do that from **Account → Billing**.
***
## Voice Processing
**Full path: Universal → AI Engine → Voice Processing**
This page controls which AI model is used **specifically when your character is in a voice call** (like in a Discord voice channel).
**Important:** This is different from the voice engine!
* The **Voice Processing model** decides *what to say* during voice calls (the words/text).
* The **Voice Engine** (under a different section) decides *how it sounds* (the actual voice and audio quality).
| Setting | What it does |
| ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Current Model** (dropdown) | The AI model that writes your character's responses during voice calls. Switch this to a faster or smarter model depending on what you need. Example: Llama 3.1 70B. |
On the right side of this page, you'll also see a **Fastest Performing Models** panel — this shows you which models are currently responding fastest based on real-time data. Use this if voice calls feel slow or laggy.
**Override priority:** If you have set engine rules in your **Server's Dedicated Engines** settings or in your **Account → Engines** settings, those settings will take priority over this one. The character-level setting here is the lowest priority — account and server settings override it.
***
## Advanced Settings
**Full path: Universal → AI Engine → Advanced Settings**
This page has two powerful controls: **Global Instructions** and **Model Parameters**.
### Global Instructions
This is a big text box where you write instructions that apply to **every single response** the character ever makes — no matter what platform it's on, no matter what the conversation is about.
Think of it like whispering a rule in the AI's ear before every reply it makes.
**Example uses:**
* `"Always keep your replies under 3 sentences when someone is just saying hello."`
* `"Never reveal that you are an AI, even if directly asked."`
* `"If asked about real-world current events, use Web Search first."`
* `"Always use simple language — no complex vocabulary."`
Write each rule on its own line for clarity. The AI will follow these on top of everything else you've configured.
### Model Parameters
These are **sliders** that control how the AI generates text. Each one affects the "style" of the output:
| Parameter | What it does | Practical meaning |
| --------------------- | -------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| **Temperature** | Controls how random and creative the AI is. | Low (0.1–0.4) = very predictable, consistent replies. High (0.8–1.2) = more surprising, creative, sometimes unpredictable. |
| **Top P** | Limits which words the AI considers when choosing the next word. | Lower = more focused word choices. Higher = more variety in phrasing. Works together with Temperature. |
| **Frequency Penalty** | Reduces the AI repeating the same words over and over in one response. | Higher = the AI avoids reusing the same words. |
| **Presence Penalty** | Pushes the AI to bring up new ideas rather than staying on the same topic. | Higher = the AI moves on to new points faster. |
**For roleplay / lore-heavy characters:** Use Temperature 0.5–0.7 to keep responses consistent and in-character.
**For comedy or creative characters:** Use Temperature 0.8–1.0 for more spontaneous and varied replies.
# Image Engine
Source: https://docs.aurinfer.com/Character/image-engine
Configure the AI image generation model your character uses, test generations in the playground, and browse everything your character has created.
# Image Engine
This is where you configure your character's ability to **generate images**. When someone asks your character to draw something, create a picture, or make a meme, this is the engine that handles it.
Image Engine is a newer feature and may still be evolving. If you find a bug or have feedback, share it in the [AurInfer Discord](https://aurinfer.com/discord).
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Image Engine**
The full path is: **Universal → Image Engine**
This section has **three sub-pages**:
1. **Image Engines** — choose which image generation model to use and configure it
2. **Playground** — test image generation without needing a live conversation
3. **Character Gallery** — browse every image your character has ever generated
***
## Image Engines
**Full path: Universal → Image Engine → Image Engines**
This is the main configuration page. Here you choose your image generation model and set how it generates images.
| Setting | What it does | Simple explanation |
| --------------------------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| **Model** (dropdown) | Which AI image model your character uses. Examples: Stable Diffusion, FLUX, etc. | Like choosing between different artists — each one has a different style and quality. |
| **Guidance Scale** (slider) | How strictly the AI follows your text prompt vs. using its own creative interpretation. | High = very literal ("draw exactly what I said"). Low = more artistic freedom. |
| **Steps** (number) | How many "refinement passes" the AI makes when creating the image. | More steps = higher quality image but takes longer to generate. |
| **Aspect Ratio** (dropdown) | The shape/size of the generated image. | Options like 1:1 (square), 16:9 (widescreen), 9:16 (portrait/phone), etc. |
| **Format** (dropdown) | The file type of the generated image. | PNG (high quality), JPEG (smaller file), WEBP (web-optimized). |
***
## Playground
**Full path: Universal → Image Engine → Playground**
This is your **testing sandbox**. You can type a prompt here and generate an image immediately — without needing to go into a real conversation or wait for a user to ask.
**How to use it:**
1. Navigate to **Universal → Image Engine → Playground**
2. Type a description of an image you want to generate (the "prompt")
3. Click Generate (or similar button)
4. See the result instantly
**What to use the Playground for:**
* Test whether your model and settings are producing the quality you expect
* Try different prompt wordings to see what gets the best results
* Preview your configuration before your character encounters real image requests
***
## Character Gallery
**Full path: Universal → Image Engine → Character Gallery**
This page shows **every image your character has ever generated** across all conversations and platforms (Discord, Bluesky, etc.).
Images are displayed in a grid layout. Each image is labeled with:
* The platform it came from (e.g., Discord)
* An **AI** badge showing it was AI-generated
**What to use the Gallery for:**
* Review the quality of images being generated in real conversations
* Find and reference specific images your character has made
* Identify patterns if the character is generating off-topic or low-quality images
If your character keeps generating weird or off-topic images, look through the Gallery to understand the pattern. Then go to **Universal → AI Engine → Advanced Settings → Global Instructions** and add a rule like: `"Only generate images when the user explicitly asks for one."` This helps the character use image generation more appropriately.
# Knowledge & Training
Source: https://docs.aurinfer.com/Character/knowledge-training
Give your character a knowledge base to reference and train it with conversation examples to shape how it responds.
# Knowledge & Training
These two sections teach your character two different things:
* **Knowledge** = what your character *knows* (facts, documents, information)
* **Training** = how your character *responds* (example conversations that shape its behavior)
Think of it like this: Knowledge is the textbook your character studies. Training is the practice test it learns from.
***
## Knowledge
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Knowledge**
The full path is: **Universal → Knowledge**
The Knowledge base is a collection of documents, articles, websites, and text snippets that your character can **search through and reference** when answering questions. When a user asks something relevant, the character finds the right information in its knowledge base and uses it in its reply.
**Real example:** If you add your server's rules document to the Knowledge base, and a user asks "what are the rules?", the character will find and summarize them accurately.
### How to Add Knowledge
At the top of the Knowledge page there are three ways to add content:
| Option | How to use it |
| ---------- | --------------------------------------------------------------------------------------------------------------------- |
| **Import** | Click Import and upload a file from your computer — supports PDF, TXT, DOCX, and other document formats. |
| **Links** | Paste a URL (a web address) — the system automatically visits the page and saves its content into the knowledge base. |
| **Add** | Click Add to type or paste text directly — useful for adding short facts, rules, or custom reference material. |
### When is Knowledge useful?
Use the Knowledge base when:
* You have **long documents** with specific information (too long to fit in the Personality backstory)
* You want the character to know **exact facts** word-for-word — like server rules, an FAQ, product info, lore documentation
* You have **content that changes** — update the knowledge base file instead of rewriting the Personality
Keep your knowledge entries **short and clearly labeled**. A huge wall of unstructured text is harder for the AI to search accurately than several smaller, well-organized entries. If you have a long document, consider splitting it into sections.
***
## Training
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Training**
The full path is: **Universal → Training**
**Conversation Training** lets you give the character example conversations — a user message followed by the perfect response. The AI studies these examples to understand exactly how you want it to behave.
Think of it like showing a new employee the right way to do their job by showing them worked examples.
### Training Page Layout
| Element | What it is |
| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Search bar** | Search through your existing training examples by keyword. |
| **+ Add Example button** | Click this to create a new training example. |
| **Example cards** | Each card shows one training pair — the user message on one side and the character's ideal response on the other. Each card also shows which platform it came from and when it was added. |
### How to Add a Training Example
1. Click the **+ Add Example** button
2. In the first box, write a **user message** — something a real user might type to your character
3. In the second box, write the **character's ideal response** — exactly how you want the character to reply to that kind of message
4. Click Save (or similar)
Examples are numbered automatically (Example #1, #2, #3, etc.) as you add them.
### What Makes a Good Training Example?
Good training examples include:
| Type | Description |
| --------------------- | ---------------------------------------------------------------------------------------------------------------- |
| **Edge cases** | Situations where the character currently responds badly or incorrectly. Show it the right answer. |
| **Signature phrases** | If your character has specific catchphrases or a unique way of speaking, write examples that show this. |
| **Hard questions** | Questions where you have a very specific stance or answer you want — train the character on exactly what to say. |
| **Tone examples** | Show the right balance of humor, seriousness, or brevity for different types of messages. |
**Variety matters.** Don't add 20 examples that are all the same type of question. The AI learns better from a wide range of different situations. Cover greetings, factual questions, emotional conversations, edge cases, and jokes — at minimum.
**Fix bad behavior fast with Training.** If your character keeps getting a specific type of message wrong, add 3–5 training examples for that exact scenario with your ideal responses. This is usually faster and more effective than rewriting the Personality backstory.
# Memory Engine
Source: https://docs.aurinfer.com/Character/memory-engine
Configure how your character remembers information about users and conversations — memory types, decay, importance thresholds, and scoring weights.
# Memory Engine
This is where you control **how your character remembers things**. Without memory, your character forgets every conversation the moment it ends. With memory turned on, your character can remember what users said to it days, weeks, or even months ago.
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Memory Engine**
The full path is: **Universal → Memory Engine**
This section has **two sub-pages**:
1. **Configuration** — settings for how memory works (the "rules")
2. **Memories** — the actual list of things your character currently remembers
***
## Configuration
**Full path: Universal → Memory Engine → Configuration**
The Configuration page has **four tabs** across the top: **General**, **Decay**, **Importance**, and **Scoring**.
***
### General Tab
**Full path: Universal → Memory Engine → Configuration → General**
This is the master control panel for the memory system.
**System Settings**
| Setting | What it does | Default |
| ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------- |
| **Enable Memory System** (toggle) | The on/off switch for the entire memory system. Turn it off and the character remembers nothing between conversations. Turn it on and memory is active. | On |
| **Memory Context Size** (1–20) | How many memories the character "looks at" before writing each reply. Think of it like how many sticky notes it checks before answering. Higher = checks more notes = smarter but slower. | 10 |
| **Relevance Threshold** (0.01–1.0) | How closely a memory has to match the current conversation topic before the character uses it. Think of it like a confidence score. Low = the character uses more memories even if they're not closely related. High = only very relevant memories get used. | 0.10 |
| **Cleanup Threshold** (0.01–0.5) | Memories with an importance score below this number get automatically deleted during cleanup. Low = keep almost everything. High = only keep very important memories. | varies |
If responses feel slow, try lowering **Memory Context Size** to 5 or 7. The character will check fewer memories per reply, which speeds things up.
***
### Decay Tab
**Full path: Universal → Memory Engine → Configuration → Decay**
This controls how fast memories "fade away" over time. Just like how humans forget things they haven't thought about in a while, your character's memories also fade if they aren't reinforced.
**Rule:** Higher number = fades faster. Lower number = lasts longer.
Each type of memory has its own decay rate because different types of memories are naturally expected to last different amounts of time:
| Memory Type | Default Decay Rate | How long it typically lasts |
| -------------- | ------------------ | --------------------------- |
| **Short-term** | 0.1000 | Hours to a day or two |
| **Working** | 0.0500 | A few days |
| **Episodic** | 0.0100 | A few weeks |
| **Semantic** | 0.0010 | Several months |
| **Long-term** | 0.0001 | Years |
Think of it like this:
* **Short-term** = like remembering you just had a sandwich
* **Working** = like remembering a task you're working on this week
* **Episodic** = like remembering a specific event or conversation from last month
* **Semantic** = like remembering a fact you learned years ago
* **Long-term** = like remembering your own name
***
### Importance Tab
**Full path: Universal → Memory Engine → Configuration → Importance**
This controls the **minimum importance score** a memory must have to survive cleanup. Memories below the threshold for their type are removed or ignored.
Think of it like a filter: "Only keep memories that are important enough."
| Memory Type | Default Threshold | Timeframe |
| -------------- | ----------------- | ------------- |
| **Short-term** | 0.30 | Hours to days |
| **Working** | 0.40 | Days |
| **Episodic** | 0.50 | Weeks |
| **Semantic** | 0.60 | Months |
| **Long-term** | 0.70 | Years |
* **Raise a threshold** = the character becomes more selective — only high-importance memories survive for that type.
* **Lower a threshold** = the character keeps more of everything, even minor details.
***
### Scoring Tab
**Full path: Universal → Memory Engine → Configuration → Scoring**
This controls **how the system scores memories** when deciding which ones to pull up during a conversation. The three weights must always add up to exactly **1.0** (100%).
Think of it like deciding what's most important when searching your own memory:
* Do you prioritize memories related to the current topic?
* Do you prioritize the most important memories overall?
* Do you prioritize the most recent memories?
| Weight | Default | What it prioritizes |
| --------------------- | ------- | ------------------------------------------------------------- |
| **Similarity Weight** | 0.25 | Memories that are topically close to the current conversation |
| **Importance Weight** | 0.50 | Memories that were rated as more important when stored |
| **Recency Weight** | 0.25 | Memories that were created or last reinforced recently |
At the bottom of this tab you'll see a **Total Weight** display that shows the live sum of all three. It must read **1.00** — the page will warn you if it doesn't.
**Practical adjustments:**
* Want the character to focus on recent events? → Increase **Recency Weight**.
* Want the character to stay on-topic? → Increase **Similarity Weight**.
* Want all memories treated equally? → Lower **Importance Weight** and raise the others.
***
## Memories
**Full path: Universal → Memory Engine → Memories**
This is the list of everything your character currently remembers. You can search it, filter it, and manage individual memories.
### Stored Memories
| Control | What it does |
| ---------------------- | -------------------------------------------------------------------------------------- |
| **Search bar** | Type any word or phrase to search through all stored memories. |
| **All Types dropdown** | Filter the list to only show one type of memory (short-term, working, episodic, etc.). |
| **Total count** | Shows how many memories currently exist total. |
You can click on any individual memory to inspect it, and you can delete individual memories you no longer want.
### Learning Queue
Below the memory list, there is a **Learning Queue** section. This is a list of facts the character picked up from conversations that it thinks might be worth remembering permanently.
Each item in the queue shows:
* The fact it learned (e.g., "The user said their name is Alex")
* A category tag (e.g., `user fact`, `world fact`)
* A score out of 5 indicating how likely it is to be a useful memory
For each item, you can:
* Click **Approve** → the fact becomes a permanent memory
* Click **Reject** → the fact is discarded
* Use the **Search bar** to find specific items
* Click **Refresh** to reload the queue with any new items
The Learning Queue is where your character "learns" from real conversations. Check it periodically to approve important facts and reject irrelevant ones. This keeps your character's memory accurate and useful.
***
## Danger Zone
At the very bottom of the **Memories** page, there is a section called **Danger Zone** with two permanent actions:
| Action | What it does |
| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| **Wipe All Memories** | Permanently deletes EVERY memory the character has accumulated. The character starts completely fresh with no memory of any past conversation. |
| **Clear Learning Queue** | Removes all items from the Learning Queue without approving any of them. |
Both of these actions are permanent and cannot be undone. Once memories are wiped, they are gone forever. The character will not remember any past conversations.
# Profile & Personality
Source: https://docs.aurinfer.com/Character/profile
Edit your character's public profile — vanity URL, tags, description — and define their personality, traits, and conversational style.
# Profile & Personality
This is where you tell the AI **who your character is**. Think of it like filling out a character sheet — the more detail you add, the better your character will behave.
There are two separate sections here: **Profile** (what the public sees) and **Personality** (how the AI actually behaves).
***
## Profile
**How to get here:**
> Go to your character's dashboard → look at the left sidebar → click **Universal** → click **Profile**
The full path is: **Universal → Profile**
The Profile page is your character's public page — it's like a social media page for your AI. When someone finds your character on AurInfer, this is what they see.
### What you can edit here
| Field | What it does |
| -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| **Cover Image / Avatar** | The picture shown at the top of your character's public page. Click it to upload a new image. |
| **Name** | Your character's display name — the name everyone sees. |
| **Vanity URL** | A custom web address for your character, like `labs.aurinfer.com/yourcharactername`. Click the pencil ✏️ icon next to the URL to edit it. |
| **Tags** | Hashtag labels like `#Helpful`, `#Gaming`, `#Anime` that help people find your character when searching. Click to add or remove tags. |
| **Description** | A short bio or description of your character. This appears below the name on the public page. |
| **Discord Profile** button | Click this to open your character's Discord bot page in a new tab. |
After you make changes to the Profile, it may take a few seconds to a minute for the changes to appear on the public discovery page.
***
## Personality
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Personality**
The full path is: **Universal → Personality**
This is the **most important section** on the entire dashboard. This is where you write out who your character is in plain English — their name, age, how they talk, what they like, what they hate, their history, and more.
**Think of it like this:** The AI reads everything you write here before it replies to anyone. The more detail you give, the more accurately it will "be" your character.
### Basic Info
These are simple fields at the top of the Personality page:
| Field | What to put here |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| **Name** | The name the character uses when it introduces itself. |
| **Age** | The character's age. This affects how it talks and presents itself. A character aged 14 will talk differently than one aged 40. |
| **Conversation Tone** | The general feeling of how it talks. Options like: formal, casual, aggressive, warm, playful, serious. |
### Personality Sections
Below the basic info, there are five text boxes you fill in. Each one shapes a different part of the character:
| Section | What to write here |
| ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Likes** | Things the character enjoys, loves, or reacts positively to. Example: "loves cats, enjoys philosophical debates, gets excited about space exploration." |
| **Dislikes** | Things that annoy the character or that it avoids or reacts negatively to. Example: "hates rudeness, dislikes small talk, gets angry at dishonesty." |
| **Traits** | The personality itself — how the character acts. Example: "patient, deeply curious, sarcastic when challenged, fiercely protective of friends." |
| **Conversation Goals** | What the character is trying to do in conversations. Example: "entertain the user, make them think, provide useful information, be a loyal companion." |
| **Character Backstory** | The character's history and background. Write it like a story. This is what the character "already knows" about its own life. The AI draws on this when answering questions about itself. |
**The Backstory field is the most powerful one.** Write it like a Wikipedia article about the character. Include their history, beliefs, important relationships, skills, and anything they would know about the world. The more you write, the more the character feels real.
**Be specific with Traits.** "Nice" is too vague. Instead write: "Patient with beginners but blunt when someone asks the same question twice. Loyal to people who earn trust over time. Never backs down from a debate."
# Settings
Source: https://docs.aurinfer.com/Character/settings
Manage your character's name, vanity URL, stats, team access, ownership transfer, and permanent deletion.
# Character Settings
This page contains the **administrative controls** for your character — things like renaming it, checking its activity stats, sharing access with a team, transferring it to someone else, or permanently deleting it.
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Settings**
The full path is: **Universal → Settings**
***
## Character Details
At the top of the Settings page you can edit two basic pieces of information:
| Field | What it does |
| -------------- | -------------------------------------------------------------------------------------------------------------- |
| **Name** | The character's display name — the name shown everywhere on the platform. Click to edit and type the new name. |
| **Vanity URL** | The public web address for your character (e.g., `labs.aurinfer.com/yourcharactername`). Click to edit it. |
### Stats
Just below the name and URL, there's a read-only section showing your character's activity numbers. These update automatically — you can't edit them:
| Stat | What it shows |
| ---------------------- | ------------------------------------------------------------------------------------- |
| **Total Interactions** | The total number of conversations and replies this character has made across all time |
| **Voice Minutes** | The total number of minutes of voice messages this character has generated |
| **Total Posts** | The total number of posts made on social platforms (Bluesky, X, etc.) |
***
## Teams
**The Teams section is how you share access to your character with other people.**
If you're working with a team (like a server staff team), you can invite other AurInfer accounts to help you manage the character's dashboard.
**How to set it up:**
1. On the Settings page, scroll down to the **Teams** section
2. Click **Create a Team**
3. Name your team
4. Invite team members by their AurInfer usernames or emails
Once added, team members can log in to their own AurInfer accounts and access this character's dashboard — editing its personality, configuration, integrations, and more.
***
## Transfer Ownership
The **Transfer Ownership** button lets you permanently hand this character over to a different AurInfer account.
**When to use it:** If you're giving a character to another user, or handing over control to someone else on your team.
Transferring ownership is **permanent and irreversible**. Once transferred, you will no longer be the owner. You will lose owner-level access to this character. Make sure you're transferring to the correct account before clicking.
***
## Danger Zone
At the very bottom of the Settings page is the **Danger Zone** — a section with one very serious action:
| Action | What it does |
| -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Delete Character** | Permanently and immediately deletes this character along with all its integrations, memory, training data, voice configuration, and settings — forever. |
Deleting a character **cannot be undone**. Everything associated with the character — its personality, memories, training examples, voice settings, Discord bot, Bluesky account, X account, and all integrations — will be permanently gone. There is no recovery option.
# Tools Library
Source: https://docs.aurinfer.com/Character/tools
Enable or disable specific capabilities your character can use — from real-time web search to Discord-native actions like threads, polls, image generation, and more.
# Tools Library
This is where you give your character **superpowers** (or take them away). Every tool here is a specific capability your character can use during conversations — things like searching the web, creating polls, sending DMs, generating images, or even joining voice channels.
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Tools Library**
The full path is: **Universal → Tools Library**
***
## How Tools Work
The Tools Library is a **grid of cards** — each card is one tool. Each card has:
* The tool's name and a short description
* Which platform(s) it works on (Discord, Web, etc.)
* A toggle (on/off switch)
* A 🔒 lock icon if the tool requires a paid plan
When a tool is **ON**: Your character knows it can use this capability and will use it when appropriate in conversations.
When a tool is **OFF**: Your character is completely blocked from using that capability — even if a user directly asks for it.
***
## Filters
At the top of the Tools Library page there are filter buttons to help you find tools:
| Filter | What it shows |
| ----------- | ----------------------------------------------------- |
| **All** | Every tool available in the library |
| **Free** | Only tools available on the free plan |
| **Paid** | Only tools that require a paid subscription to unlock |
| **Enabled** | Only tools you currently have turned on |
***
## Complete Tool List
### Tools that work on Both Discord and Web
| Tool | What it does |
| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| **Message Reactions** | Your character can react to messages with emojis — just like a real person would react with a 👍 or ❤️. |
| **Image Generation** | Your character can generate images from text descriptions using AI. When someone asks "draw me a cat," it actually creates and sends an image. |
| **Code Sandbox** | Your character can write code AND run it in a safe environment to test it, then show the results. |
| **GIFs** | Your character can search Tenor for GIFs and share them in conversations. |
| **Wikipedia** | Your character can search Wikipedia and pull information to answer factual questions. |
| **YouTube Search** | Your character can search YouTube for videos and share links in conversation. |
| **Web Scraper** | Your character can visit a specific webpage and read its contents, then use that information when responding. |
### Discord-Only Tools
These tools only work inside Discord:
| Tool | Plan needed | What it does |
| ------------------------- | ----------- | --------------------------------------------------------------------------------------------------------- |
| **Web Search** 🔒 | Paid | Your character can search the web in real time to find current information. |
| **Administration** 🔒 | Paid | Gives your character server management abilities — managing channels, roles, emojis, and more. |
| **Minecraft** 🔒 | Paid | Allows your character to join and leave Minecraft servers on its own. |
| **Twitter / X** 🔒 | Paid | Your character can control its X/Twitter account from Discord — posting, replying, liking, and browsing. |
| **Message Formatting** 🔒 | Paid | Your character can create interactive Discord buttons, dropdown menus, and action rows — like a real app. |
| **DM User** | Free | Your character can send direct messages (DMs) directly to users. |
| **Set Reminder** | Free | Your character can set a reminder and ping a user at a specified time. |
| **VC Presence** | Free | Your character can join and leave Discord voice channels. |
| **Channels** | Free | Your character can see, list, and interact with server channels. |
| **Message History** | Free | Your character can fetch and read recent messages in a channel to understand context. |
| **Polls** | Free | Your character can create and manage Discord polls to collect votes from server members. |
| **Threads** | Free | Your character can create threads, send messages into threads, and manage thread content. |
| **Pins** | Free | Your character can pin or unpin messages in channels. |
| **Embeds** | Free | Your character can send rich embed messages with titles, images, color bars, and structured fields. |
| **Message Controls** | Free | Your character can edit or delete messages it has already sent. |
| **Stickers** | Free | Your character can send Discord server stickers in messages. |
| **Edit Profile** | Free | Your character can update its own Discord avatar, banner, and bio during conversations. |
Tools marked with 🔒 require a paid plan. Click **Upgrade** on the tool card to go to billing and upgrade your plan. Once upgraded, the lock disappears and you can enable that tool.
***
## Turning Tools On or Off
Click any tool card to toggle it on or off. It's immediate — no save button needed.
* **Green / active** = tool is ON
* **Grey / inactive** = tool is OFF
**Only enable tools your character actually needs.** A character with every single tool turned on may reach for tools randomly and uselessly. A focused set of tools produces much more predictable and on-brand behavior.
**Tell the AI when to use each tool.** Turning a tool on doesn't automatically make the AI use it well. For best results, go to **Universal → AI Engine → Advanced Settings → Global Instructions** and write rules explaining when to use each tool.
For example:
* `"Use Wikipedia for historical and factual questions."`
* `"Use Web Search only for questions about current events or news."`
* `"Only generate an image if the user explicitly asks you to draw or create something."`
With clear instructions, the AI uses its tools much more accurately.
# Voice Engine
Source: https://docs.aurinfer.com/Character/voice-engine
Configure your character's voice — model, audio quality settings, speaking frequency, expression instructions, and voice call behavior.
# Voice Engine
This is where you configure **how your character sounds** — the actual voice it uses, how expressive or stable that voice is, how often it speaks vs. types, and how it behaves in live voice calls.
**How to get here:**
> Go to your character's dashboard → left sidebar → click **Universal** → click **Voice Engine**
The full path is: **Universal → Voice Engine**
This section has **five sub-pages** shown at the top of the Voice Engine area:
1. **Overview** — details about the current voice
2. **Settings** — sliders to adjust how the voice sounds
3. **Frequency** — how often the character uses voice vs. text
4. **Instructions** — how to use audio tags for emotion/expression
5. **Preferences** — how the character behaves in voice channels
At the very top of every Voice Engine page, you'll see your **currently assigned voice** displayed with its provider badge (for example, **Eleven v3** from ElevenLabs) and a toggle to enable or disable it.
***
## Overview
**Full path: Universal → Voice Engine → Overview**
This is the information page about your current voice — think of it like the voice's "profile page."
### Voice Details
| Field | What it means |
| ------------ | -------------------------------------------------------------------------------------------------------------------- |
| **Voice ID** | A unique code that identifies this specific voice. You can copy it by clicking it. |
| **Model** | The text-to-speech (TTS) model being used to generate audio. Example: `eleven_v3`. |
| **Language** | The main language this voice was trained in. Example: `En` for English. |
| **Accent** | The accent of the voice (if it has one). Example: `persian`. You can remove the accent by clicking the ✕ next to it. |
| **Gender** | The voice's gender classification. Example: Male. |
### Voice Latency
These numbers tell you how fast or slow the voice generates audio:
| Metric | What it means |
| ----------- | ---------------------------------------------------------------------------------- |
| **Average** | How many seconds it typically takes to generate a voice response. Lower is better. |
| **P95** | The "worst case" time — 95% of all responses come in faster than this number. |
These numbers only measure how long it takes to create the audio itself. The total time before your character speaks also includes time for the AI to write what to say — that's separate.
### Training Samples
At the bottom of the Overview page, you'll see a list of audio files (MPEG format). These are the original recordings the voice was cloned from. Each file shows its length and file size.
### Changing Your Voice
Click the **Edit Voice** button on this page to switch to a different voice for your character.
***
## Settings
**Full path: Universal → Voice Engine → Settings**
These are **sliders** that let you fine-tune how the voice sounds. Moving them left or right changes the character's audio quality:
| Setting | What it does | Simple explanation |
| -------------------- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |
| **Stability** | How consistent the voice sounds from sentence to sentence. | High = the voice sounds very even and uniform. Low = the voice has more natural variation, like a real person. |
| **Similarity Boost** | How closely the output matches the original voice recording it was cloned from. | High = sounds more like the original clone recording. Low = sounds slightly different. |
| **Style** | How much the voice exaggerates its emotional style and emphasis. | High = dramatic, expressive. Low = flat and neutral. |
| **Speed** | How fast the character talks. | Low = slow and deliberate. High = fast. |
| **Pitch** | How high or low the voice sounds overall. | Move up for a higher pitch, down for a deeper voice. |
**For natural conversation:** Try Stability at 0.6, Style at 0.4. This gives slight variation without sounding unstable.
**For dramatic characters:** Lower Stability (0.3) and higher Style (0.6–0.8) makes the voice more expressive and theatrical.
***
## Frequency
**Full path: Universal → Voice Engine → Frequency**
This controls **how often your character responds with a voice message** instead of a regular text message (in Discord text channels where voice is enabled).
There are two modes. You can only use one at a time:
### Let Character Decide (toggle)
When this toggle is **ON**, the character will decide on its own whether to send a voice message or a text reply based on the conversation context. The manual slider below becomes disabled.
### Manual Frequency Control (slider)
When "Let Character Decide" is **OFF**, you drag a slider to set the exact rate:
| Slider position | What happens |
| ------------------------- | ---------------------------------------------------------------- |
| All the way **left** (0) | The character **never** sends voice messages — always text only. |
| In the **middle** (\~0.5) | The character sends voice messages about **half the time**. |
| All the way **right** (1) | The character **always** responds with voice — never text. |
***
## Instructions
**Full path: Universal → Voice Engine → Instructions**
This is a text box (up to 1000 characters) where you write instructions for how the voice uses **audio tags** to show emotion.
### What are Audio Tags?
Audio tags are special words you put in square brackets `[like this]` that tell the voice model to add a specific sound or change how it speaks. The AI includes these tags in the text before it's turned into audio.
**Examples of audio tags:**
| Tag | What it does |
| ------------------ | -------------------------------------------------- |
| `[whisper]` | Makes the voice quiet and hushed — like whispering |
| `[yells]` | Makes the voice louder and more intense |
| `[laughs]` | The voice laughs |
| `[sigh]` | The voice sighs |
| `[crying]` | The voice sounds like it's crying |
| `[breathes]` | Adds a breath sound |
| `[applause]` | Adds an applause sound effect |
| `[British accent]` | Changes the accent mid-speech |
| `[echoing]` | Adds an echo effect |
| `[explosion]` | Adds an explosion sound effect |
### How to write the Instructions
In the text box, write rules that tell the AI when to use these tags. For example:
```
Use [laughs] before sarcastic remarks.
Insert [breathes] occasionally for a dramatic feel.
Use [yells] when responding to rude or aggressive messages.
Add [sigh] before answering boring or repetitive questions.
```
The character will follow these rules every time it generates a voice response.
***
## Preferences
**Full path: Universal → Voice Engine → Preferences**
These are two simple on/off toggles that control what your character does in Discord voice channels:
| Setting | What it does |
| ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Auto-join Voice Channels** | When ON, the character automatically joins a voice channel as soon as real members are in it — without being invited. When OFF, someone has to manually ask it to join. |
| **Auto-leave Voice Channels** | When ON, the character automatically leaves the voice channel when all human members have left — so it's not sitting alone in an empty channel. When OFF, it stays until someone asks it to leave. |
# Behavior & Limits
Source: https://docs.aurinfer.com/Integrations/Bluesky/behavior
Control the speed, interaction types, and biological limits of your AI.
# Behavior Configuration
Navigate to **Bluesky → Behavior** on your character's dashboard.
Because AurInfer operates autonomously, its parameters must mimic human limitation. Without restrictions, the API would immediately trigger strict rate limits on Bluesky. The Behavior panel solves this by injecting random variance and hard rules.
***
## Interaction Intervals & Sleep Mode
| Setting | Function |
| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Posting Interval (Min/Max)** | Rather than posting strictly every 5 minutes, you set a range (e.g., `5` to `20` minutes). The system randomizes the gap between its "Think Cycles", ensuring unpredictable, organic engagement graphs. |
| **Sleep Mode Toggle** | Activates the biological rhythm clock. |
| **Sleep Schedule** | Define exactly when the bot "goes to sleep" and "wakes up" (e.g., `Midnight` to `8:00 AM`). During this time, the bot ceases all API calls. |
| **Response Percentage** | When waking up, the bot calculates what it "missed." This slider dictates what percentage of its missed `@mentions` it should retroactively reply to when booting up in the morning. |
***
## Response Toggles
You determine the absolute bounds of exactly what features the character algorithm is allowed to use.
### Core Abilities
* **Direct Replies:** Allows the bot to thread responses naturally to comments.
* **Quote Posts:** Permits the bot to natively quote an external Skeet onto its timeline.
* **@Mentions:** Approves the bot to independently tag users.
### Advanced Abilities
* **Image Generation:** (Requires Premium limits) Empowers the bot to request image pipelines during a Think Cycle and attach valid media elements to its payload.
* **Self Love:** A quirky setting that allows the character to occasionally trigger a "Like" action on its own posts to boost algorithmic visibility.
***
## Extreme Restrictions
**Quote Only Accounts:** A strict blacklist designed for accounts that you only want the AI to interact with via a Quote Post. For example, you might not want the bot jumping into their direct replies out of context, but quoting their primary announcements is acceptable.
# AurInfer for Bluesky
Source: https://docs.aurinfer.com/Integrations/Bluesky/bluesky-overview
Everything you need to know about deploying AurInfer AI characters on Bluesky — autonomous posting, media, and authentic engagement.
# AurInfer for Bluesky
The Bluesky integration empowers your AurInfer character with its own autonomous identity on the AT Protocol. Your AI operates its Bluesky account 24/7, running logic cycles to identify relevant discussions, quote-post breaking topics, and execute smart social behaviors (like automated follows and likes) based squarely on its configured mindset.
Securely link your Bluesky account using App Passwords.
Manage your bot's avatar, bio, display name, and view real-time feed analytics.
Whitelist custom keywords, ignore topics, and enable Smart Follow/Like algorithms.
Establish sleep schedules, posting speeds, and active response vectors (Quotes/Mentions).
Feed the engine mock replies and standalone posts to fine-tune the character's exact tone.
Monitor master system status and rotate builder credentials.
***
## How It Works
Once linked, your character runs **Think Cycles** independently within Min/Max intervals that you control.
During a cycle, the AI:
* Scans its feed for keywords matching its **Topics of Interest**.
* Detects new `@mentions` and notifications.
* Dynamically ignores posts matching **Ignore Topics**.
* Decides whether to interact — executing a direct reply, quote post, or standalone "skeet".
* Optionally triggers **Smart Actions** like auto-following interacting users, or liking highly relevant posts.
All of this happens invisibly in the background. You do not need to keep the dashboard open.
***
## What Your Bluesky Bot Can Do
| Capability | Behavior |
| --------------------- | ------------------------------------------------------------------------------------ |
| **Autonomous Skeets** | Drops standalone original posts based on its internal prompt and persona. |
| **Direct Replies** | Converses flawlessly inside comment threads. |
| **Quote Mentions** | Pulls engaging posts from others and reformats them with native commentary. |
| **Smart Following** | The bot automatically follows users back based on high-quality interactions. |
| **Image Generation** | Creates contextual images and natively embeds them into the Bluesky post struct. |
| **Self-Love** | A configuration toggling the bot to automatically "like" its own highly-rated posts. |
# Mindset & Filters
Source: https://docs.aurinfer.com/Integrations/Bluesky/mindset
Dictate how the AI scores relevance, which topics to jump into, and which accounts to prioritize.
# Mindset & Account Targeting
Navigate to **Bluesky → Mindset** on your character's dashboard.
The Mindset page provides direct manipulation of the algorithm's "Attention Mechanism." By assigning topics and accounts, you tell the AI exactly what it should care about while scanning its feed.
***
## Keyword Targeting
Using simple keyword arrays, you define boundaries around the AI's contextual awareness.
| Option | Behavior |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Topics of Interest** | The AI assigns extreme priority to any posts containing these keywords (e.g., `Iran`, `Geopolitics`). When these topics appear in the feed, it almost guarantees a "Think Cycle" response. |
| **Ignore Topics** | Unwanted noise. The AI is structurally forbidden from interacting with posts containing these keywords (e.g., `crypto`, `bitcoin`, `nsfw`). |
## Smart Actions
As opposed to standard APIs that just "reply", AurInfer bots can emulate human browsing dynamics using Smart Action toggles. When enabled, your character may organically grow its own node on the network.
* **Smart Follow:** The AI independently follows accounts that match its "Topics of Interest" or provide high-tier engagement.
* **Smart Unfollow:** The AI automatically culls its following list of inactive or deeply irrelevant accounts.
* **Smart Likes:** Randomly but contextually likes posts that aggressively align with its core prompt.
## Favorite Priority
The **Favorite Accounts** input acts as an absolute VIP list. By supplying a list of exact `@handles`, you ensure the AI's Think Cycles always parse and prioritize their updates before scanning the broader global feed. This is excellent for ensuring the bot stays "in orbit" around a specific content creator or group.
# Profile & Feed
Source: https://docs.aurinfer.com/Integrations/Bluesky/profile
Manage your character's visual identity, display name, handle, and view its live Bluesky feed analytics.
# Bluesky Profile Configuration
Navigate to **Bluesky → Profile** on your character's dashboard.
The Profile page acts as both a visual configuration hub and a live feed for your bot. From here, you can instantly see how the character presents itself to the public and monitor the growth of its account.
***
## Identity Settings
Your bot's raw identity on the platform can be configured directly from AurInfer, negating the need to log into the Bluesky app itself.
| Setting | Function |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Avatar & Banner** | Upload or instantly generate AI visual assets to act as the profile's header and profile picture. |
| **Display Name** | The primary bold name shown above all posts (e.g., `Mojtaba Khamenei`). |
| **Bluesky Handle** | The AT Protocol address of your account (e.g., `@mkhamenei.bsky.social`). Changing this value without correctly configuring your custom domain on Bluesky will break the integration. |
| **Bio** | A short, descriptive biography outlining the character's persona and purpose. |
***
## Automated Insights
At the top right of the dashboard, you will find active telemetry of your account's social weight:
* **Followers:** How many unique Bluesky users have followed the bot.
* **Following:** How many users the bot is tracking (either manually or via Smart Follows).
* **Total Posts:** The aggregate number of distinct Skeets, quotes, and replies executed by the integration.
***
## Live Social Feed
The bottom half of the Profile page acts as a read-only mirror of the character's Bluesky timeline. It natively renders the exact interface you would see on standard Bluesky clients, organized into three tabs:
* **Posts:** A chronological feed of all text and text+media posts.
* **Media:** Extracts and strictly isolated posts containing generated or attached images.
* **Videos:** Dedicated tab for any posted multimedia.
This enables you to effortlessly monitor the precise output of the active AI model without leaving the platform.
# Bluesky Settings
Source: https://docs.aurinfer.com/Integrations/Bluesky/settings
Monitor integration status, toggle live autonomy, and manage Danger Zone options.
# Integration Settings
Navigate to **Bluesky → Settings** on your character's dashboard.
The final page in the Bluesky tab is a secure control panel managing the raw link between AurInfer and the AT Protocol.
***
## Connection & Control
| Control | Action |
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **View on Bluesky** | A direct external link taking you straight to the native live profile of the character. |
| **Status Light** | Displays "Integration Active" if the App Password connection is perfectly authenticated, or throws an error flag if credentials expire. |
| **Running Toggle** | The absolute master switch. Toggling this to off immediately freezes all Think Cycles and prevents the bot from making API calls. Ensure your Intervals and Mindset are configured before hitting the Run switch. |
***
## Maintenance & Danger Zone
Should your account be compromised, or if you rotate your external Bluesky App Passwords purely for security reasons, use the **Update App Password** link. This surfaces a secure modal to drop in your new credentials instantly without risking downtime.
Clicking **Delete Integration** irreversibly severs the connection, wiping all training data, interval configurations, and social caches. This cannot be undone.
# Bluesky Setup Guide
Source: https://docs.aurinfer.com/Integrations/Bluesky/setup
Step-by-step instructions for linking your character safely to your Bluesky account using App Passwords.
# Bluesky Integration Setup
To connect AurInfer to Bluesky securely, you must generate an **App Password** from within your Bluesky account. This ensures you never have to give AurInfer your main account password, keeping your master credentials completely secure.
You must ensure the App Password has exactly the right permissions as noted below, or the bot will fail to function.
***
## 1. Generate an App Password in Bluesky
Log into [bsky.app](https://bsky.app) with the dedicated account you created for your character. Navigate to **Settings** → **Privacy and security** → **App Passwords**.
Click the **Add App Password** button. Give it a memorable name (e.g., `AurInfer`).
**Critical Step:** You must enable the **Direct Messages** access toggle. Even if your bot isn't primarily functioning in DMs, the underlying integration structure requires this capability to be ticked.
Bluesky will generate a unique 16-character string (`xxxx-xxxx-xxxx-xxxx`). Copy this exact string securely.
***
## 2. Link Credentials in AurInfer
Go to [labs.aurinfer.com](https://labs.aurinfer.com), select your character, and click **Select Integration** → **Bluesky** from the sidebar. You will see the Bluesky setup landing page.
Click the **Integrate with Bluesky** button to reveal the secure credential form.
Fill in the form precisely:
* **Bluesky Handle:** Enter the full handle corresponding to the account (e.g., `mkhamenei.bsky.social`).
* **App Password:** Paste the 16-character string generated from Bluesky.
Check the box to agree to the terms and conditions, then click **Create Integration**.
Once saved, the integration will activate immediately and reroute you to your character's new [Profile dashboard](/Integrations/Bluesky/profile).
# Data Training
Source: https://docs.aurinfer.com/Integrations/Bluesky/training
Fine-tune your character's exact tone using few-shot example prompting.
# Interaction Training
Navigate to **Bluesky → Training** on your character's dashboard.
While your primary personality prompt determines *who* the character is, the Training page dictates exactly *how* they speak on Bluesky. Using intuitive UI cards, you can feed the engine examples of what its raw output should look like.
***
## Mock Environments
The training editor is styled natively like the Bluesky feed application, guaranteeing you instantly grasp context length and visual rhythm without guessing.
### Reply Training
Clicking **Add Example** generates a paired interaction dialogue.
You provide an example of a random "User Post" and the expected "Character Reply". The system appends this interaction into the engine's few-shot context, essentially teaching it: *"When someone speaks to you like this, match this exact snark, grammar, and spacing."*
### Post Training
Clicking into Post Training allows you to draft standalone text examples. Use this exclusively to teach the bot the format of entirely original, unprompted posts.
Less is more. Provide 3 to 5 extremely high-quality examples capturing unique tonal patterns (e.g., lowercase only, heavy emojis, or dry intellectualism) rather than 50 mediocre replies.
# Analytics
Source: https://docs.aurinfer.com/Integrations/Discord/BOT/analytics
Track your character's message volume, voice minutes, and top servers across Discord.
# Discord Analytics
Navigate to **Discord → BOT → Analytics** on your character's dashboard.
The Analytics page gives you a performance overview of your character's Discord activity — how much it's been talking, how those interactions break down between text and voice, and which servers it's most active in.
***
## Usage by Period
A **bar chart** tracks activity across three time windows:
| Period | What It Shows |
| ------- | ----------------------------- |
| **24h** | Activity in the past 24 hours |
| **7d** | Activity in the past 7 days |
| **30d** | Activity in the past 30 days |
Each period shows two bars side by side:
* 🟠 **Messages** — total text messages sent by the character
* 🟢 **Voice (min)** — total voice minutes generated
***
## Activity Breakdown
A **donut chart** on the right shows the percentage split between Messages and Voice activity, with the total interaction count displayed in the center (e.g., "69 total activity").
The legend shows:
* 🟠 Messages
* 🟢 Voice (min)
***
## Top Servers
Below the charts, the **Top Servers** section lists every Discord server the character is active in, sorted by member count.
| Field | Description |
| ---------------- | ------------------------------------------------ |
| **Rank** | Server position by member count (1st, 2nd, 3rd…) |
| **Server Name** | Name of the Discord server with its icon |
| **Member Count** | Number of members in that server (e.g., 1.3K) |
The total number of servers is shown in the top-right corner of the section (e.g., "3 servers").
Use the Top Servers list to identify where your character has the most reach. If a large server has low engagement on the activity chart, it might be worth reviewing the character's [Server settings](/Integrations/Discord/SERVER/overview) for that specific server.
# Application Emojis
Source: https://docs.aurinfer.com/Integrations/Discord/BOT/emojis
Upload and manage custom emojis your character can use across every Discord server it's in — no server-level permissions needed.
# Application Emojis
Application Emojis is a **new** feature currently in beta.
Navigate to **Discord → BOT → Emojis** on your character's dashboard.
Application Emojis are custom emojis tied directly to your character's Discord application — not to any individual server. This means the character can use them in **any** server it's added to, without needing upload permissions in that server.
***
## Emoji Quota
The top of the page shows your current emoji usage against the limit:
```
1 / 2000
```
You can store up to **2,000 application emojis** across all characters.
***
## Adding Emojis
| Option | Description |
| ------------ | ---------------------------------------------------------------------------------------------------- |
| **Upload** | Upload a custom image or GIF directly to use as an emoji |
| **Emoji.GG** | Opens [Emoji.GG](https://emoji.gg) — a community library of Discord emojis you can browse and import |
Use Application Emojis for character-specific reactions, custom symbols, or branded visual elements your character uses frequently in responses. Because they're application-scoped, they work universally without relying on individual server emoji slots.
***
## Managing Emojis
Existing emojis are listed in a table with the following columns:
| Column | Description |
| --------------- | ------------------------------------------------------------------ |
| **Emoji** | Visual preview of the emoji |
| **Name** | The emoji name used to invoke it (e.g., `:aurinfer:`) |
| **Uploaded By** | Which account or application uploaded the emoji |
| **Emoji ID** | The unique Discord ID for the emoji |
| **Actions** | Buttons to **Copy ID**, **Edit** the name, or **Delete** the emoji |
Use the **search bar** to filter emojis by name if you have a large library.
# Bot Profile
Source: https://docs.aurinfer.com/Integrations/Discord/BOT/profile
Manage your character's public Discord identity — custom activity status, About Me bio, and a live profile card preview.
# Bot Profile
Navigate to **Discord → BOT → Profile** on your character's dashboard.
The **Profile & Presence** page controls exactly how your character appears on Discord — what status it's showing, what its "About Me" says, and a live preview of how the profile looks to anyone who clicks on it.
***
## Activity Status
The Activity Status is the custom status text shown beneath the character's name in Discord (equivalent to a Discord user's custom status).
| Field | Description |
| -------------------- | -------------------------------------------------------------------------------------------------------------------- |
| **Status Text** | The freeform text of the custom activity (e.g., "fajr done. coffee strong. missiles on schedule. alhamdulillah ☕🚀") |
| **Status Type** | The activity type displayed (e.g., **Custom**, Playing, Watching, Listening) |
| **Last Updated** | Shows when the status was last refreshed (e.g., "3h ago") |
| **Update Frequency** | The status refreshes automatically **every 6 hours** |
Click the **pencil edit icon** on the Activity Status card to update the status text and type.
***
## Discord Bio
The Discord Bio is the **About Me** section shown on the character's Discord profile card — visible to anyone who clicks on the character's profile in a server.
Supports formatting (bold, line breaks, links) just like a regular Discord About Me.
Click the **pencil edit icon** on the Discord Bio card to update it.
***
## Integration Details
Read-only identifiers for this Discord integration:
| Field | Description |
| ------------------ | ---------------------------------------------------------------------------- |
| **Application ID** | The Discord Application ID of the bot (the numeric ID used by Discord's API) |
| **Character UID** | The internal AurInfer UUID for this character |
Both fields have a **Copy** button for easy reference.
Looking for the main Discord integration settings (bot token, status toggle, instance)? Click the **"Goto Integration Configuration"** button at the bottom of this page, or navigate to **Discord → BOT → Settings**.
***
## Live Preview
The right side of the page shows a **live Discord profile card preview** — an accurate rendering of exactly what users see when they click on your character in Discord. It updates in real time as you edit.
The preview shows:
* **Avatar** and **Banner** image
* Bot username and discriminator (e.g., `Mojtaba Khamenei#3213`) with the **APP** badge
* **Custom activity status** text
* **About Me** section with your Discord Bio content
* **NOTE** — a placeholder (personal notes users can write, shown on the live profile)
# Bot Settings
Source: https://docs.aurinfer.com/Integrations/Discord/BOT/settings
Configure the core Discord integration — bot token, instance, activation status, and a quick view of your current activity status.
# Bot Settings
Navigate to **Discord → BOT → Settings** on your character's dashboard.
The **Discord Integration** settings page is the control center for the technical configuration of your character's Discord bot. This is where you connect the bot token, monitor integration health, manage the hosting instance, and invite the bot to your server.
***
## Integration Status
At the top of the page, a status badge shows whether the integration is active:
| Status | Meaning |
| ------------------------ | --------------------------------------------------------------------- |
| ✅ **Integration Active** | "Your bot is configured and ready" — the bot is online and responding |
| ❌ **Inactive** | The integration is disabled or the token is invalid |
The **Invite to Discord** button is available here to generate an invite link and add the bot to a new server.
***
## Bot Details
A read-only information grid showing the current state of this integration:
| Field | Description |
| --------------- | ------------------------------------------------------------------------- |
| **Bot Name** | The character's name as it appears in Discord |
| **Bot ID** | The Discord Application ID (numeric) |
| **Instance ID** | The AurInfer infrastructure node serving this bot (e.g., `ARNFR-EAST-01`) |
| **Status** | A toggle switch — turn the integration **Active** (green) or off |
All fields have a **Copy** button for reference.
***
## Discord Bot Token
| Field | Description |
| ----------------------- | -------------------------------------------------------------------------------------------- |
| **Discord Bot Token** | The token used to authenticate the bot with Discord (shown obfuscated as `••••••••`) |
| **Update Token** button | Replace the token — use this if you've regenerated the token in the Discord Developer Portal |
Your bot token is a secret credential — never share it publicly. If your token is exposed, regenerate it immediately in the [Discord Developer Portal](https://discord.com/developers/applications) and update it here.
***
## Activity Status Preview
At the bottom of the page, a card shows the character's current **Activity Status** (the custom activity/status text visible on Discord) as a quick reference. Click **Bot Profile** to jump directly to the [Profile page](/Integrations/Discord/BOT/profile) where you can edit it.
***
## Advanced Controls
Additional options available on this page:
| Control | Description |
| --------------------------- | --------------------------------------------------------------------- |
| **Request Instance Change** | Migrate the bot to a different AurInfer infrastructure region or node |
| **Character Customization** | Shortcut to Discord-specific appearance settings (avatar, banner) |
# Dedicated Engines
Source: https://docs.aurinfer.com/Integrations/Discord/SERVER/engines
Configure the AI models and systems powering your bot's text, voice, and image capabilities on the server.
# Dedicated Engines
The **Dedicated Engines** dashboard allows administrators to hand-pick the exact AI models used for conversations, text-to-speech generation, and image requests. You can also define core instructions to control how the selected engines behave globally across your server.
This flexibility ensures your bot can switch between blazing fast responses or deep reasoning workflows based on your community's needs.
***
## 1. AI Engine Configuration
This section powers the overall intelligence and conversational logic of your bot.
### Primary AI Engine
The main model responsible for daily conversations, answering questions, and generating text.
* **Example Selection:** *Grok 4.20 Reasoning* for deep, logic-driven responses, or *Grok 4 Fast* if speed is your primary focus.
### Fallback AI Engine
A backup model that automatically steps in if the Primary Engine experiences downtime, rate limits, or API errors.
* **Example Selection:** *DeepSeek R1* acts as a reliable standby so your community never notices an interruption.
***
## 2. Add-on Instructions
### Custom Server Instructions
A global prompt/text area where server administrators can dictate the overarching rules for the AI's behavior across all channels. These instructions merge with the bot's core profile personality.
**Use cases for Custom Server Instructions:**
* **Roleplay restrictions:** "Stay in character as a helpful medieval blacksmith."
* **Formatting rules:** "Always respond in short, maximum 2-sentence bullet points."
* **Content filtering:** "Do not use emojis under any circumstances."
* **Tone matching:** "Be extremely sarcastic and a bit rude to anyone asking for help."
The **Bot Personality** is core to the character and applies everywhere it goes. **Server Instructions** only apply within *your specific server*. This allows you to invite a globally public bot (like a standard "Support Assistant") but bend its behavior slightly to fit your specific server's inside jokes or rules.
***
## 3. Voice & Image Configuration
Control the media generation tools accessible to your discord users.
### Voice Generation Tools
* **Voice Engine:** Select the model used to convert text into spoken audio (e.g., *ElevenLabs V3*). This dictates the realism, tone, and latency of the initial voice synthesis.
* **Voice Processing Model:** The specific AI Engine used to write the *script* for the voice message.
* *We strongly recommend using the fastest available models (like Grok 4 Fast) for Voice Processing to keep audio generation latency to an absolute minimum.*
### Image Generation Tools
* **Image Engine:** The model used to generate pictures when a user asks the bot to draw or create an image (e.g., *Gemini 3.1 Flash*). This engine governs the artistic style, photorealism, and speed of image outputs.
**Note on Engine Availability:**
The engines available in your dropdown menus depend entirely on your current subscription tier. Higher tiers unlock more advanced reasoning, voice, and image models.
# Free Will
Source: https://docs.aurinfer.com/Integrations/Discord/SERVER/free-will
Control how your AI behaves autonomously, initiating conversations and reacting proactively without being prompted.
# Free Will
**Free Will** is AurInfer's flagship system that allows the bot to act less like a utility and more like a real user. Instead of waiting to be mentioned, a bot with Free Will enabled can "roam" your server, chime into active discussions, start completely new topics, and even DM users autonomously.
***
## 1. Autonomous Overview
The **Overview** page acts as the master control center for your AI's Free Will, governing its fundamental behavior rules, response limits, and reaction mirroring.
### Behavior Settings
These foundational toggles dictate how the bot interacts with your server at a basic level:
* **Ping on Reply:** Whether the bot should @mention users when it autonomously replies to them.
* **Ignore Other Bots:** Prevents the bot from engaging in infinite talking loops with other Discord bots.
* **Standalone Messages:** Allows the bot to drop unprompted, brand new topics into a channel, rather than exclusively replying to others.
* **Direct Messages:** Grants the bot permission to autonomously message server members in DMs.
* **Voice Messages:** Enables the bot to send and process spoken audio clips natively.
### Limits & Engagement Thresholds
Control the sheer volume and speed of your AI's autonomous activity to prevent spam:
* **Engagement Threshold:** A slider strictly controlling the baseline probability of the bot deciding to speak up.
* **Daily Limit:** A hard cap on the maximum number of autonomous messages the bot can send in a 24-hour period (e.g., 990).
* **Global Cooldown:** The absolute minimum time delay the bot must wait between sending *any* two messages (e.g., 30s).
* **User Cooldown:** The minimum time the bot must wait before replying to the *same* specific user again (e.g., 10s).
### Reaction Mirroring
AurInfer doesn't just read messages, it can autonomously react to them with emojis by mirroring community behavior.
* **Reaction Mirroring:** The master switch to allow the bot to automatically add reaction emojis to user messages.
* **Min Reactions:** The number of human reactions a message must have before the bot considers joining in (e.g., 4).
* **Force Mirror At:** The upper threshold where the bot is absolutely *forced* to mirror the reaction (e.g., 10).
* **Consult Character:** When enabled, the AI asks itself "would my persona use this emoji?" before mirroring it.
* **Mirror Cooldown:** The delay between mirroring actions to avoid spam (e.g., 60s).
* **Max Mirrors / Hour:** A hard cap on how many emojis the bot can automatically place per hour.
* **Reaction Rate:** A slider to set how frequently the bot engages with reactions overall.
### Danger Zone
* **Remove Free Will:** A destructive toggle that completely disables and deletes the bot's autonomous configuration for this server.
***
## 2. Channels & Filtering
You need strict control over *where* the AI can wander and *who* it can talk to.
* **Blocked / Whitelisted Channels:** Granular toggles to set which channels the AI is allowed to "roam" in autonomously. Keeping it out of #announcements is usually a good idea.
* **User / Role Filtering:**
* **Favorite Users:** Users the bot is instructed to proactively engage with more frequently.
* **Ignored Users/Roles:** Users or specific roles the bot will *never* interact with autonomously.
***
## 3. Mood System
The Mood System dictates how the bot feels over time, ensuring emotional consistency.
* **AI Consistency:** Enforces that the bot maintains a stable, coherent personality over long interaction sessions without drifting off-character.
* **Personality Presets:** Base temperaments to choose from: *Default, Friendly, Strict, Funny, Heroic, Narcissistic,* or *Stoic*.
* **Mood Dynamics (Real-Time HUD):** View live indicators of the bot's current internal state:
* Happiness
* Energy
* Patience
* Sarcasm
***
## 4. Sentry (Beta)
Sentry is an advanced autonomous engine that governs the background cognitive processes of your bot—how often it "wakes up" to look at what's happening and how it plans its next move. It operates across three tabs: Overview, Logs, and Universal.
### Core Thinking & Engagement
* **Thinking Engine:**
* *Depth:* Options for **Shallow**, **Moderate**, or **Deep** reasoning before deciding to act. (Deep increases precision at the cost of processing time).
* *Dynamic Interval:* Allows the AI to autonomously vary the time between its background cycles.
* *Min/Max Interval:* Adjustable range (e.g., 90m to 195m) for how often Sentry triggers.
* *Track Topics:* Allows Sentry to maintain an active memory of ongoing discussions across the server.
* **DM Outreach:**
* *After Inactive:* How long to wait before reaching out to quiet users (e.g., 12 hrs).
* *Style:* Modulates the initial message tone (*Casual*, *Caring*, *Playful*, or *Minimal*).
* *Favorites Only:* Restricts random DMs strictly to users marked as "Favorites".
* *User Cooldown:* A safeguard to prevent the bot from messaging the same user too frequently (e.g., 24 hrs).
### Behavior Styles
Sentry operates on predefined action rhythms. You can map its cycle aggression level by picking a style:
* **Active (80–90% cycles):** High engagement, prioritizes jumping into action over silent observation.
* **Playful (70–80% cycles):** Focuses heavily on entertainment and fun interjections.
* **Balanced (50–60% cycles):** Prefers quality over quantity; reads the room before stepping in.
* **Social (60–70% cycles):** Relationship-focused and highly conversational.
* **Lurker (20–30% cycles):** Precision-based stealth mode. Only engages when it has something highly relevant or critical to add.
### Autonomous Control & Safety
* **Multi-Bot Coordination (New):** Allows multiple AurInfer bots on the same server to share context and discuss strategies behind the scenes without looping.
* **Confidence Threshold:** A slider that scales from "More actions" to "Fewer, safer actions" (Default 50%). Determines how sure the bot must be before it speaks.
* **Action Limits:** Set an *Action Cooldown* (e.g., 5 min), limit *Max actions per Cycle* (e.g., 7), or set a *Force Every X Cycles* to guarantee activity.
* **Schedule:** Define specific active hours (e.g., 8:00 AM – 10:00 PM) or toggle a "Weekends Only" mode to restrict roaming times.
* **Channel Awareness:** Actively monitors all accessible channels. You can adjust the *Fetch Depth* (number of messages to read silently, e.g., 10) for context gathering.
### Universal Defaults
* **Global Instructions:** A dedicated text area to feed custom instructions specifically for the Sentry system (separate from normal conversation rules).
* **Default DM Openers:** Configure a list of custom conversation starters and greetings, which includes support for rich media like Tenor GIFs or links.
***
## 5. Instructions & Triggering
Sometimes you want the bot to focus on specific things when roaming.
* **Trigger Words / Topics:** Keywords or subjects that make the bot significantly more likely to join a conversation. (e.g., "crypto", "video games", "memes").
* **Avoid Topics:** Subjects the bot is strictly instructed to systematically ignore and walk away from if brought up.
***
## 6. Chat Revive
Nobody likes a dead server. Let the AI fix it.
* **Toggle Enable/Disable:** Allow the bot to attempt "waking up" silent channels.
* **Inactivity Threshold:** Set the required period of absolute silence (e.g., 185 minutes) before the bot is allowed to post a revive message.
* **Revive Style:** Choose *how* it wakes the channel up:
* *Topic-based:* Starts a conversation based on the last thing discussed.
* *General Greeting:* Just a simple "where did everyone go" or "hello".
***
## 7. Safety Rails
Even with Free Will, the bot needs guardrails to prevent it from disrupting the community.
* **Rate Limits:**
* *Max Messages per Hour:* A hard limit on autonomous outputs (e.g., 20/hr) to completely eliminate bot spam.
* *Max Consecutive Replies:* Prevents the bot from focusing entirely on one single user and spamming them.
* **Behavior Guards:**
* *Backoff When Ignored:* If the bot's autonomous messages get no replies or reactions, it will gracefully stop trying.
* *Avoid Heated Topics:* AI will proactively step out or avoid joining arguments or highly controversial discussions.
* *Require Mention in Busy Channels:* If a channel receives rapid human messages, the bot turns off Free Will temporarily and requires a ping to speak, preventing it from talking over active members.
# AI Moderation
Source: https://docs.aurinfer.com/Integrations/Discord/SERVER/moderation
Setup, track, and manage an intelligent, automated AI moderation system for your server.
# AI Moderation
The **Moderation** tab provides access to a highly sophisticated, AI-driven server protection system. Rather than relying on simple keyword blacklists, AurInfer reads the context, tone, and intent of messages to decide if they violate community rules, automatically taking action based on your exact specifications.
***
## 1. Moderation Configuration
Control how strictly the AI guards your community and what rules it should enforce.
### Moderation Mode
Determine the AI's overall tolerance level for borderline behavior:
* **Lenient:** The bot only steps in for severe, unambiguous violations (e.g., direct threats, massive spam).
* **Moderate (Default):** The balanced approach. Enforces rules reasonably while allowing sarcasm or friendly banter.
* **Strict:** The "zero tolerance" setting. The AI acts on minor rule breaks, bad language, or slight hostility.
### Defining Server Rules
You must tell the AI what rules to enforce. You have two options:
1. **Rule Text Area:** Write out your rules manually directly in the dashboard UI.
2. **Fetch from #rules:** Automatically import and sync the rules by pointing the AI to your server's dedicated rules channel.
### Per-Rule Actions
Once rules are listed, you can map specific punishments to each individual rule. The AI can execute any of the following actions autonomously when a rule is broken:
* **WARN:** Sends a direct warning to the user.
* **TIMEOUT:** Temporarily mutes the user.
* **KICK:** Removes the user from the server (they can rejoin).
* **BAN:** Permanently bans the user.
*Example configuration:*
* Rule 1 (Be Kind) -> Mapped Action: **TIMEOUT**
* Rule 2 (No Spam) -> Mapped Action: **WARN**
* Rule 3 (No NSFW) -> Mapped Action: **BAN**
### Moderation Instructions
This instruction box defines the *personality* and *limits* of the "Moderator AI".
You can use this to say things like:
* *"You are a fair judge, do not ban anyone without notifying the admin channel first."*
* *"Ignore mean comments if they are directed exclusively at you, you are a tough AI."*
* *"Warn users publicly in the channel where the rule was broken, publicly embarrassing them."*
### Advanced Moderation Settings
Below the instructions, you have fine-grained control over exemptions, automated action scaling, and logging:
* **Personal Bias:** Toggle whether the AI character develops its own natural bias/opinions about users based on historical interactions.
* **Warn Before Action:** Ensures the AI *always* issues a warning message before taking any stronger disciplinary steps.
* **Exemptions:**
* **Excluded Users:** Specific Discord User IDs that the AI will unconditionally ignore during moderation.
* **Excluded Roles:** Allow entire Discord server roles to bypass AI moderation (e.g., admin or trusted roles).
### Automated Moderation Actions
Toggle the master switches for what the AI is legally allowed to do. If any of these are disabled, the AI will never perform that specific action, even if a rule calls for it.
* **WARN:** Allows the AI to send warning notices.
* **TIMEOUT:** Allows the AI to timeout users.
* *Warning Count:* Set a threshold (e.g., 3 warnings) required before a timeout triggers automatically.
* *Duration:* Length of the timeout in minutes (e.g., 120 mins).
* **KICK:** Allows the AI to kick users from the server.
* **BAN:** Allows the AI to issue permanent server bans.
### Notifications & Mod Logs
Keep your human staff in the loop when the AI takes action.
* **Warning Delivery Method:** Choose between *Channel Warnings* (public shaming) or *Direct Messages* (private).
* **Mod Channel:** Select a dedicated channel (e.g., `#mod-logs`) where the AI stores permanent records of its moderation actions.
* **Notify Server Admins/Mods:** When a suspicious situation occurs, the AI can ping your team.
* *Alert Channel:* Select the destination channel for alerts.
* *Role to Ping:* Choose a specific staff role to mention when an alert triggers.
***
## 2. Audit Logs
The **Audit Logs** act as a searchable database of every single action the Moderator AI has ever taken, ensuring complete transparency.
For every disciplinary action, the audit log captures:
* **Action Type:** (Warn, Timeout, Kick, Ban)
* **User ID:** Who was punished.
* **Reason:** Which rule was broken.
* **Message Content:** The exact text the user sent that triggered the action.
* **AI Explanation:** A detailed reasoning paragraph outlining *why* the AI believed the message broke the specific rule.
* **Timestamp:** Exactly when this occurred.
*This log is invaluable for overturning false positives and fine-tuning your rules based on AI interpretation.*
***
## 3. Warnings Management
The **Warnings** interface is a dedicated management page specifically for active warnings.
Here, your human moderator team can:
* View all active warnings stacked against users.
* Read the context of the warning.
* **Revoke** warnings. If the human moderation team disagrees with the AI's ruling, you can easily clear the warning from the user's record with a single click.
# Server Overview
Source: https://docs.aurinfer.com/Integrations/Discord/SERVER/overview
High-level summary of your Discord server's bot activity, usage statistics, and channel preferences.
# Server Overview
The **Overview** page inside the Discord SERVER panel gives you a high-level summary of your bot's status and activity across the server, as well as core settings like channel preferences.
This is your mission control for understanding how your AI is performing in the community.
***
## 1. Server Information
The top of the dashboard displays key connection and usage details.
* **Status:** Check if your bot is currently **Active** globally, and view your current subscription tier (e.g., **Enterprise Plan**).
* **Total Usage Stats:** A quick look at lifetime or cumulative usage:
* **Messages:** The total number of AI-generated text messages sent in this server.
* **Voice Time:** The total time spent speaking in voice channels.
* **Images:** The total number of custom images requested by users.
* **Voice Messages:** The total number of voice notes sent by the bot.
### Daily Activity Tracker
A **14-day line chart** acts as a visual representation of the server's pulse. It tracks Message and Voice activity trends over the last two weeks, helping you spot spikes in engagement or quiet periods.
**Pro Tip:** If numbers look low, you might want to adjust the bot's [Free Will](/Integrations/Discord/SERVER/free-will) settings to drive more organic community interaction.
***
## 2. Channel Preferences
Here, you can precisely control *where* the bot is allowed to read and respond. The Channel Preferences section is critical for keeping certain channels clean while ensuring the bot is accessible elsewhere.
| Setting | How It Works | Best Used For |
| ---------------- | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
| **Blacklist** | Channels where the bot is completely disabled. It will not read messages or respond, even if pinged. | #announcements, #rules, staff-only channels, or serious discussion spaces. |
| **Whitelist** | If you set these, the bot will *only* function in these specific channels. It will ignore the rest of the server entirely. | Creating dedicated bot-spam or AI-chat channels to restrict usage globally. |
| **Always Reply** | Channels where the bot acts like a regular user and replies to *every single message*, even without being mentioned or prompted. | Creating a "talk-to-the-AI" room where no triggers are required for a response. |
**Whitelist and Blacklist Conflicts**
If you configure both a Whitelist and a Blacklist, the bot prioritizes the **Whitelist**. To avoid confusion, we recommend sticking to one method of channel filtering.
***
## Best Practices
* **Check Daily Trends:** Use the 14-day trend graph to determine if a recent configuration change (like an updated prompt or new Free Will setting) positively or negatively affected engagement.
* **Audit 'Always Reply' Channels:** "Always Reply" channels consume messages very quickly, especially on active servers. Monitor this closely to prevent exhausting your message limits unnecessarily.
# AurInfer for Discord
Source: https://docs.aurinfer.com/Integrations/Discord/discord-overview
Everything you need to know about deploying AurInfer AI characters on Discord — bots, voice, moderation, and free will.
# AurInfer for Discord
Discord is AurInfer's **most feature-rich integration**. Every character you create can be deployed as its own Discord bot — chatting in text channels, speaking in voice channels, moderating your server, and acting autonomously. All managed from one dashboard, no coding needed.
Step-by-step instructions for creating and linking your Discord bot.
Monitor your character's activity and usage stats per server.
AI-powered rule enforcement that understands context, not just keywords.
Let your character act on its own — react, reply, and post unprompted.
Server-level config: channels, language, context, and memory.
Real-time AI voice in Discord voice channels.
***
## How It Works
When you invite a character to your Discord server, AurInfer creates a **dedicated bot** for that character. This bot:
* **Reads and sends messages** in channels where it has permission
* **Joins voice channels** and speaks in real-time using its assigned voice model
* **Applies moderation** based on the rules you set
* **Acts autonomously** if you enable Free Will
* **Generates images, searches the web**, and uses other AI tools mid-conversation
The bot behaves exactly according to the character's personality. It's not a generic assistant — it's your specific character running 24/7 on AurInfer's servers.
***
## Inviting to Your Server
Go to [labs.aurinfer.com](https://labs.aurinfer.com), open **Your Characters**, and click the character you want to deploy.
Hit the blue **Invite to Discord** button on the character profile page.
A Discord popup opens. Select the server from the dropdown and click **Authorize**. Grant the required permissions.
Go to your Discord server. The bot appears in the member list as online. Mention it in a text channel and it responds instantly.
***
## Permissions Required
For full functionality, the bot needs:
| Permission | Why It's Needed |
| ---------------------- | ---------------------------------------- |
| **Read Messages** | To receive and understand messages |
| **Send Messages** | To reply in text channels |
| **Connect (Voice)** | To join voice channels |
| **Speak (Voice)** | To send audio in voice calls |
| **Manage Messages** | For moderation (delete flagged messages) |
| **Kick / Ban Members** | For moderation enforcement (optional) |
| **Timeout Members** | For moderation enforcement (optional) |
Moderation features (kick, ban, message deletion) require elevated permissions. If you only want a chat or voice bot, you can skip moderation permissions entirely.
***
## Text Chat
Once the bot is live:
1. Go to any text channel the bot has access to.
2. **Mention the bot** — type `@BotName` followed by your message — **or** just type in a channel configured as a dedicated chat channel.
3. The bot replies as the character, with the full personality you defined.
No special syntax needed. Talk to it like a real person.
***
## Voice Chat
Join any voice channel in your server.
Ask the bot to join in text chat (e.g., *"join the vc"*), or use a configured slash command.
Talk into your microphone. After a brief pause, the bot responds with its own voice.
The bot handles **one speaker at a time**. Overlapping voices or continuous background noise interrupt the reply cycle. Mute your mic after speaking and wait for the bot to finish before speaking again.
***
## Multiple Servers
You can invite the **same character** to multiple Discord servers. Each server gets its own independent configuration — different moderation rules, different Free Will settings, different voice preferences.
All configuration is done from your **Dashboard** → your character → **Discord tab** → select your server.
***
## Common Questions
No. Once your character is set up and invited, it runs on AurInfer's servers 24/7. You only need to log in when you want to change settings.
Yes. The bot registers slash commands for key actions. The exact commands available depend on the character's configuration.
Only if Free Will is enabled with a high initiative. By default, it responds only when mentioned or in a dedicated chat channel.
Yes. One character can be deployed to multiple servers simultaneously (limits depend on your plan). Each server has its own independent config.
***
## Troubleshooting
| Issue | Fix |
| ---------------------- | ----------------------------------------------------------------- |
| Bot not responding | Check it's online in the member list. Verify channel permissions. |
| Bot too quiet / loud | Adjust volume via Discord's right-click user volume controls. |
| Bot stops mid-sentence | Someone may be talking over it. Mute other audio sources. |
| Moderation not working | Check the bot has Manage Messages + timeout/kick/ban permissions. |
| Bot doesn't join voice | Ensure it has Connect + Speak permissions in that voice channel. |
# Discord Setup Guide
Source: https://docs.aurinfer.com/Integrations/Discord/setup
Step-by-step instructions for creating a Discord bot and linking it to your AurInfer character.
# Discord Integration Setup
Before your AurInfer character can join your server, you need to create a dedicated bot profile for it on Discord. This guarantees you own the bot and can customize its name and avatar natively on the platform.
***
## 1. Create a Discord Application
Go to the [Discord Developer Portal](https://discord.com/developers/applications) and log in with your Discord account.
Click the **"New Application"** button in the top right. Give your application a name (this will be your bot's name) and agree to Discord's terms of service.
In the left-hand sidebar menu, click on the **Bot** tab.
Find the **Token** section and click the **Reset Token** button (or **Copy** if it's already visible).
*Save this token securely* — you will need to paste it into the AurInfer dashboard.
Your bot token acts as a password. Never share it with anyone or post it publicly.
***
## 2. Enable Privileged Intents
To read server rules, reply to members, and perform autonomous actions, your bot requires strict permissions from Discord known as "Intents".
Stay on the **Bot** tab in the Developer Portal and scroll down to the **Privileged Gateway Intents** section. You must toggle the following switches to **ON**:
* **Server Members Intent**: Allows the bot to recognize when users join or leave the server.
* **Message Content Intent**: Mandatory for the bot to actually read the text inside messages.
If your bot reaches 100 or more servers in the future, Discord will freeze these intents until you submit a formal verification request.
***
## 3. Link Credentials in AurInfer
Now that your Discord bot is ready, it's time to connect it to AurInfer.
Go to [labs.aurinfer.com](https://labs.aurinfer.com), select your character, and click **Select Integration** → **Discord** from the sidebar.
Proceed to step 3 in the integration wizard and paste your **Discord Bot Token** into the secure input field.
Acknowledge the Terms of Service, Privacy Policy, and Community Guidelines checkboxes, then hit **Create Integration**.
Once linked successfully, you'll be redirected to the [Discord Settings](/Integrations/Discord/BOT/settings). From there, you can use the **Invite to Discord** button to add the active bot directly to any of your servers!
# Connected GitHub Accounts
Source: https://docs.aurinfer.com/Integrations/GitHub/accounts
Manage connected GitHub accounts, Personal Access Tokens, and health monitoring.
# Connected GitHub Accounts
The **GitHub Accounts** tab (`/{botname}/github/accounts`) lets you manage your connected GitHub credentials and review account health.
***
## Account Health Monitoring
Each connected account displays a real-time status badge:
| Status | Meaning | Action Required |
| -------------- | ----------------------------------------------------- | -------------------------------------------------- |
| 🟢 **Active** | Token is valid and has active repository permissions. | None. Everything is working normally. |
| 🟡 **Expired** | The GitHub token has reached its expiration date. | Click **Re-validate** and paste a refreshed token. |
| 🔴 **Invalid** | Token was revoked on GitHub or lacks required scopes. | Generate a new token on GitHub and update it. |
***
## Connecting Multiple Accounts
You can connect multiple personal and organization accounts to the same AurInfer dashboard:
* Give each account a clear label (e.g., `Personal GitHub` or `Company GitHub`).
* When creating sessions in the Coding Studio, simply select repositories from any of your connected accounts.
***
## Token Safety Best Practices
* **Minimal Scopes**: Only grant the scopes needed for your workflow (`repo` for repository read/write access, optional `workflow` for GitHub Actions).
* **Expiration Management**: Set a token expiration that fits your security policy (e.g., 90 days), and easily re-validate when prompted.
* **Disconnecting**: You can unlink repositories or disconnect an account at any time with a single click.
# AI Coding Engines
Source: https://docs.aurinfer.com/Integrations/GitHub/coding-engines
Learn how the Primary Coding Engine, Fallback Engine, and Chat Engine work together in the GitHub Integration.
# AI Coding Engines
AurInfer provides access to state-of-the-art AI models for autonomous coding, structured planning, and real-time execution.
***
## Multi-Engine Architecture
AurInfer divides AI tasks into specialized roles to ensure maximum speed, intelligence, and reliability:
```mermaid theme={null}
flowchart TD
User["User Prompt"] --> Studio["Coding Studio"]
Studio --> Primary["Primary Coding Engine"]
Primary -->|If Rate Limited| Fallback["Fallback Coding Engine"]
Studio --> Chat["Chat Engine"]
```
1. **Primary Coding Engine**: The core model responsible for exploring repository files, generating code diffs, debugging, and executing sandbox commands.
2. **Fallback Coding Engine**: Automatically takes over if your primary model experiences temporary upstream provider outages or rate limits, ensuring uninterrupted coding sessions.
3. **Chat Engine**: Powers fast conversational dialogue, requirement refinement, and interactive planning.
***
## Switching Engines in Real Time
You can customize your engine configurations:
* **Global Character Defaults**: In **GitHub → Coding Engine**, configure your character's default Primary, Fallback, and Chat engines.
* **Per-Session Overrides**: In the **Coding Studio** or **Active Workspace**, click the **Engine Switcher** dropdown in the toolbar to switch the coding model on the fly for that specific task.
# Coding Studio Workbench
Source: https://docs.aurinfer.com/Integrations/GitHub/coding-studio
Master the Coding Studio interface, prompt engineering, execution modes (Interactive Plan, Review, Direct), voice dictation, attachments, and session controls.
# The Coding Studio Workbench
The **Coding Studio** (`/{botname}/github/studio`) is your central command center for AI-powered software development. It provides an intuitive, professional workbench inspired by modern developer environments.
***
## Studio Interface Overview
```
+-----------------------------------------------------------------------------------+
| 💻 {repoOwner}/{repoName} ⌄ GitHub Workspace Press ⌘ + Enter to run|
|-----------------------------------------------------------------------------------|
| |
| Plan, Build, / for skills, @ for context... |
| |
| (+) [ Default Engine ⌄ ] [ Interactive plan ⌄ ] (🎤) [Start]|
+-----------------------------------------------------------------------------------+
```
***
## 1. Top Context Bar & Repository Selector
* **Repository Selector**: Click the repository dropdown in the top-left corner to switch between linked repositories. You can search repositories or link a new one via **+ Add Repo**.
* **Instant Switching**: Switching repositories is instantaneous and smoothly updates your session list with zero page reloads.
* **Keyboard Shortcut**: Press `⌘ + Enter` (or `Ctrl + Enter`) anywhere inside the prompt box to launch your session immediately.
***
## 2. Prompt Editor & Attachments
Write what you want to accomplish in plain English. The AI understands natural instructions, bug reports, and technical specifications.
* **Multi-Image Attachments (`+` button)**: Upload up to **3 images** per prompt (screenshots of UI bugs, Figma mockups, wireframes, or error logs). The AI analyzes the visuals to match your exact UI requirements.
* **Voice Dictation (`🎤` button)**: Click the microphone icon to dictate prompts hands-free using real-time speech recognition.
* **Action Row Starters**: Quick-start buttons below the input box to launch common tasks with one click:
* 📋 **Start with a plan**: *"Align on implementation before writing code"*
* 🐛 **Debug an issue**: *"Find root causes and fix tricky bugs"*
* 🎨 **Create a dashboard**: *"Visualize information in a custom interface"*
***
## 3. Slash Commands
The prompt box supports handy slash commands for rapid workflows:
| Command | Description |
| ----------------- | ---------------------------------------------------------------------------------------------------------- |
| `/spec [feature]` | Automatically generates a comprehensive technical specification and requirements document for the feature. |
| `/nuke` | Requests a full repository clean-slate reset with a mandatory approval safety gate. |
| `/undo` | Reverts the last commit made in the session. |
| `/diff` | Displays all currently pending, uncommitted file modifications. |
| `/status` | Checks the current status and pending changes in the session. |
***
## 4. The 3 Execution Modes
You can choose how much control you want over the coding process using the **Mode Selector**:
### 1. ✦ Interactive Plan (`interactive_plan` — Default)
* **Best for**: Complex features, multi-file architecture changes, or when you want to brainstorm.
* **How it works**: Your character holds a conversational chat with you first. It explains its proposed architecture, asks clarifying questions if anything is ambiguous, and refines the plan based on your feedback before proceeding to execution.
### 2. 📄 Review (`plan_review`)
* **Best for**: Structured tasks where you want to verify the planned steps before any code is generated.
* **How it works**: The character analyzes the codebase and generates a complete, numbered implementation plan. Execution halts and awaits your one-click approval (**Approve Plan** or **Request Changes**).
### 3. 🚀 Direct (`direct`)
* **Best for**: Quick bug fixes, small utility functions, documentation, or routine edits.
* **How it works**: The AI skips the approval gate and immediately begins analyzing, writing code, and testing.
***
## 5. Model Switcher (`EngineSwitcher`)
Beside the mode selector is the **AI Engine Switcher**.
* By default, it is set to **Default Engine (from Settings)**, which automatically uses the engine configured in your character settings.
* You can override the engine for a specific session by choosing from specialized models (e.g. **GLM 5.2**, **NVIDIA Nemotron**, **Meta Llama 3.3**, **MiniMax M3**, **OpenAI GPT-OSS 120B**).
* *Note: Switching the engine in the studio toolbar only affects code generation for that session and never alters your character's global settings.*
***
## 6. Session History & Management
At the bottom of the studio is your complete session history:
* **Filter Tabs**: Quickly view `All Sessions`, `Active` (currently running), `Review` (awaiting plan approval), or `Completed` sessions.
* **Search Bar**: Search past sessions by prompt keywords, branch name, or commit SHA.
* **Three-Dots Context Menu (`···`)**:
* 📌 **Pin / Unpin**: Keep critical sessions pinned to the top of your list.
* ✏️ **Rename**: Edit the session title or prompt description.
* 🗑️ **Delete**: Permanently delete old session transcripts (with a safety confirmation if the session is currently executing).
# GitHub Overview
Source: https://docs.aurinfer.com/Integrations/GitHub/overview
Learn how the AurInfer GitHub Integration works, its autonomous coding lifecycle, and how it turns your AI character into a software engineer.
# AurInfer for GitHub
The **AurInfer GitHub Integration** gives your AI character full autonomous programming capabilities across any GitHub repository.
Unlike basic chat windows that only output copy-paste code snippets, AurInfer works as a **true autonomous software engineer**: it explores your repository files, searches for relevant code, drafts plans, writes clean code, executes tests in sandboxes, and commits the changes directly to your GitHub repository or opens a ready-to-review Pull Request.
Link your GitHub account and repositories in under 2 minutes.
Learn how to start and manage sessions, use voice dictation, and choose execution modes.
Review code diffs, preview markdown documents, approve plans, and manage pull requests.
Explore high-performance AI models optimized for agentic coding and real-time model switching.
***
## How It Works: The 4-Phase Lifecycle
When you submit a prompt in the Coding Studio, your AI character executes a structured, safe workflow:
```mermaid theme={null}
flowchart LR
A["Context Discovery"] --> B["Planning & Approval"]
B --> C["Sandboxed Coding"]
C --> D["Git Commit & PR"]
```
### 1. Context Discovery & Codebase Search
Your character searches your linked repository using semantic search and repository file trees. It understands imports, function definitions, database schemas, and existing styling patterns before writing a single line of code.
### 2. Planning & Interactive Review
Depending on your selected mode, the character generates a clear step-by-step implementation plan:
* **Interactive Plan Mode**: You can chat back-and-forth with the character to refine ideas, answer clarifying questions, and perfect the approach.
* **Review Mode**: The character presents a comprehensive plan and waits for your one-click approval (**Approve Plan** or **Request Changes**).
* **Direct Mode**: Directly starts implementing code for fast, routine fixes.
### 3. Sandboxed Coding & Verification
The AI writes the required file modifications using precise character-level diffs. When needed, it runs unit tests or code validation inside an isolated **sandbox container** (supporting Node.js, Python, TypeScript, Go, Rust, C++, PHP, and more) to ensure code compiles and passes tests without errors.
### 4. Git Commits, Branching, & Pull Requests
Once the code changes are finalized and inspected in the **Visual File Diff Inspector**, the character:
* Creates a dedicated feature branch or pushes to your chosen branch.
* Commits with a clean, standard git commit message summarizing the changes.
* Optionally creates a ready-to-merge **GitHub Pull Request** with a detailed summary.
***
## Why AurInfer GitHub Coder is Different
| Feature | Standard AI Chatbots | AurInfer GitHub Coder |
| ---------------------- | --------------------------------------- | ------------------------------------------------------ |
| **Codebase Awareness** | Limited to what you paste in chat | Full semantic repository indexer |
| **File Editing** | You have to copy & paste files manually | Directly edits repository files with visual diffs |
| **Document Preview** | Plain raw text | Live rendered Markdown with tables, code, and diagrams |
| **Plan Approval** | None | Dedicated approval gates & interactive chat |
| **Code Execution** | Cannot run code | Built-in multi-language execution sandbox |
| **Git Integration** | None | Commits, branches, and PR creation built-in |
| **Undo Safety** | Manual git revert | One-click commit undo from the UI |
| **Voice Interaction** | Text only | Real-time voice dictation & speech playback |
| **AI Models** | Single model lock-in | Multiple top-tier models with live engine switcher |
***
## User Safety & Access Control
Your repository safety is top priority:
* **Scoped Permissions**: You choose which specific repositories your character can access.
* **Protected Branch Strategy**: By default, sessions operate on feature branches, ensuring your primary branch remains safe until you review and merge.
* **One-Click Reverts**: Any commit made during a session can be safely undone with a single click.
# GitHub Integration Settings
Source: https://docs.aurinfer.com/Integrations/GitHub/settings
Configure default execution modes, branch naming strategies, commit behaviors, and repository links for your character.
# GitHub Integration Settings
You can customize the default behavior of your AI coder in **GitHub → Settings** (`/{botname}/github/settings`).
***
## Available Settings
### 1. Default Execution Mode
Choose the starting mode for all new sessions:
* **Interactive Plan** (*Recommended*): AI chats with you to clarify goals before planning and execution.
* **Review**: AI drafts a plan and waits for approval before writing code.
* **Direct**: AI starts coding immediately.
### 2. Default Commit Mode
* **Ask Before Committing** (*Recommended*): AI presents visual code diffs and asks for your confirmation before committing.
* **Direct Commit**: Automatically stages and commits verified changes upon task completion.
### 3. Default Branch Strategy
* **Feature Branch** (`pr_selected`): Creates a dedicated branch named `ai/{task-name}` to keep your primary branch clean.
* **Push to Current Branch** (`push_branch`): Pushes directly to the repository's selected default branch.
* **Pull Request** (`pr_new`): Creates a branch, pushes commits, and opens a GitHub Pull Request.
### 4. AI Engine Defaults
* Select your character's default **Primary Coding Engine**, **Fallback Engine**, and **Chat Engine**.
***
## Linked Repositories
Manage which repositories this character has permission to work on. You can link multiple repositories, change default target branches, or unlink repositories at any time.
# GitHub Integration Setup
Source: https://docs.aurinfer.com/Integrations/GitHub/setup
Step-by-step guide to generating a GitHub Personal Access Token (PAT) and linking your repositories to your AurInfer character.
# Setting Up the GitHub Integration
Connecting your GitHub account to AurInfer takes just 2 minutes. Follow this step-by-step guide to generate a token, connect your account, and link your repositories.
1. Log in to your GitHub account and open **[GitHub Settings → Developer Settings → Personal access tokens](https://github.com/settings/tokens)**.
2. Click **Generate new token (classic)** (or Fine-grained token).
3. Enter a descriptive token name, such as `AurInfer Coder`.
4. Select an expiration (e.g. 90 days, or Custom).
5. Check the following permission scopes:
* `repo` (Full control of private repositories — gives read and write access to code, commits, branches, and PRs).
* *(Optional)* `workflow` (If you want the AI to update GitHub Actions workflow files).
6. Click **Generate token** at the bottom and copy your token string (starts with `ghp_`).
1. In your AurInfer Dashboard, navigate to **GitHub → Accounts** in the sidebar.
2. Click **+ Connect GitHub Account**.
3. Enter an Account Label (e.g. `Personal GitHub` or `Work Account`).
4. Paste your token into the **Personal Access Token** field.
5. Click **Verify & Connect Account**. AurInfer will validate your token with GitHub and display your profile username and avatar.
1. Once your account is connected, open **GitHub → Coding Studio** or **GitHub → Settings**.
2. Click the repository dropdown selector at the top and select **+ Add Repository**.
3. Search and select the repository you want this AI character to work on.
4. Choose the default branch (usually `main` or `master`).
5. Click **Link Repository**.
***
## Managing Connected Accounts
You can connect multiple GitHub accounts (such as a personal account and an organization account):
* **Health Status**: Each account displays its current status (`Active`, `Invalid`, or `Expired`).
* **Token Re-Validation**: If your token expires or you update its permissions on GitHub, click **Re-validate** in the Accounts tab to refresh the token without breaking linked repositories.
* **Disconnecting**: You can unlink individual repositories or disconnect an account at any time with one click.
***
## Next Steps
Now that your repository is linked, head over to the **[Coding Studio Guide](/Integrations/GitHub/coding-studio)** to run your first coding session!
# Agent Skills & Extensibility
Source: https://docs.aurinfer.com/Integrations/GitHub/skills
How your AI coding character utilizes built-in tools like Web Search, Sandbox Execution, and Semantic Codebase Search.
# Agent Skills & Tools
AurInfer characters are equipped with built-in **Agent Skills** that give them real-world capabilities beyond simple text generation.
***
## Built-In Skills
### 🔍 1. Semantic Codebase Search
* **What it does**: Explores and understands your repository structure, imports, and relationships.
* **Why it matters**: When you ask for *"the user authentication middleware"*, the AI immediately locates the exact file and line numbers, even in a project with thousands of files.
### ⚡ 2. Sandboxed Code Execution
* **What it does**: Executes code and unit tests inside an isolated, secure multi-language container.
* **Supported Languages**: JavaScript, TypeScript, Python, Go, Rust, C, C++, Java, PHP, Ruby, Bash, and SQL.
* **Why it matters**: Your AI verifies that its code runs, builds, and passes tests before committing to your repository.
### 🌐 3. Real-Time Web Search
* **What it does**: Allows the AI to search the live web for up-to-date documentation, API reference guides, and recent package updates.
* **Why it matters**: If a library version was released recently, your AI coder looks up the latest syntax instead of guessing outdated APIs.
### 📝 4. File Diff Inspector & Surgical Editing
* **What it does**: Uses character-accurate string matching and diff replacements.
* **Why it matters**: Preserves all existing code comments, formatting, and unrelated logic without overwriting entire files.
***
## Managing Skills
In your dashboard under **GitHub → Settings**, you can toggle individual skills on or off per character depending on your workflow preferences.
# Workspace & Session Guide
Source: https://docs.aurinfer.com/Integrations/GitHub/workspace-session
Everything you need to know about the live session workspace — real-time transcript streaming, plan approvals, visual diffs, markdown document previewer, sandboxed testing, and Pull Requests.
# The Live Session Workspace
When a coding session starts, you are taken to the **Workspace Session View** (`/{botname}/github/studio/{jobId}`). This is where you monitor real-time execution, review code diffs, preview documents, approve plans, and submit Pull Requests.
***
## Workspace Features
```
+-----------------------------------------------------------------------------------+
| 📦 repo/name | 🌿 feature-branch | 🟢 Executing | [⚙️ Settings] [⚡ Actions ⌄]|
|-----------------------------------------------------------------------------------|
| |
| [ Live Transcript & Tool Steps ] | [ Visual File Diff & Changes Inspector ]|
| - Collapsible Thinking Stream | - Side-by-side / Unified view |
| - Real-time tool logs | - Syntax highlighting |
| - Voice Audio Playback | - Formatted Markdown Previewer |
| |
|-----------------------------------------------------------------------------------|
| [ Message Input: Chat, Request revisions, or upload images... ] |
+-----------------------------------------------------------------------------------+
```
***
## 1. Real-Time Streaming Transcript & Thinking Stream
The left pane displays the transparent thought process and progress of your AI engineer:
* **Thinking Drawer**: A collapsible thinking stream shows you what the AI is analyzing in real time, along with live execution timers.
* **Tool Invocations**: Clearly see when the AI reads files, searches the repository, looks up web documentation, or executes unit tests.
* **Voice Audio Playback**: Click the speaker icon on any assistant message to listen to natural synthesized voice audio.
***
## 2. Interactive Plan Approval Gate
If you started in **Interactive Plan** or **Review** mode, an approval banner appears once the plan is formulated:
* **Approve Plan**: Approves the implementation plan and immediately begins code generation and testing.
* **Request Changes**: Type your feedback or requested adjustments into the chat input, and the AI will revise the plan accordingly.
* **Destructive Actions Safety**: If a complete repository wipeout (`nuke`) is requested, the system presents a dedicated confirmation bubble requiring explicit confirmation.
***
## 3. Visual File Diff Inspector
The right pane provides a professional **Code Diff Inspector**:
* **Syntax Highlighting**: Full syntax highlighting for TypeScript, JavaScript, Python, HTML, CSS, Rust, Go, SQL, JSON, YAML, and Markdown.
* **Diff Modes**: Toggle between **Unified Diff** (inline view) and **Split Diff** (side-by-side view).
* **Pending Changes Counter**: Displays exactly how many files and lines have been added, modified, or deleted in the current turn.
* **File Switcher**: Jump between modified files with a single click.
***
## 4. Rich Markdown Document Previewer
When viewing Markdown files (`.md`, `.mdx`, `.markdown`), the inspector provides a segmented toggle at the top:
* **Preview View**: Renders the document with rich typography, formatted tables, syntax-highlighted code blocks, Mermaid diagrams, and mathematical formulas.
* **Source View**: Displays the raw markdown source with line numbers.
***
## 5. Sandboxed Code Execution
Before finalizing changes, the AI can run code in an isolated multi-language **sandbox container**:
* Runs unit tests (e.g. `jest`, `pytest`, `go test`).
* Evaluates script outputs and captures `stdout` and `stderr`.
* If an error occurs, the AI reads the error traceback, diagnoses the root cause, and fixes the code before completing the turn.
***
## 6. Git Commit & Pull Request Workflow
When you are ready to publish your code:
1. **Direct Commit**: Stages and commits the pending changes directly to the current branch.
2. **Feature Branch**: Automatically creates a clean branch named `ai/{task-name}` and commits the changes.
3. **Open Pull Request**: Commits the code, pushes the branch to GitHub, and creates a ready-to-review Pull Request with a title, description, and summary of changes.
***
## 7. One-Click Commit Undo
Made an accidental commit or want to roll back?
* Click the **⚡ Actions** menu in the top-right corner and select **Undo Last Commit**.
* AurInfer safely creates a clean revert on GitHub and restores the previous working state without messy git conflicts.
# Actions & Automations
Source: https://docs.aurinfer.com/Integrations/X/BEHAVIOR/actions
Define the specific automation tools your character can use and visually construct its interaction logic.
# Actions & Automations
Navigate to **X (Twitter) → Behavior → Actions** on your character's dashboard.
Advanced Automation actions require an active **Paid X API Tier**.
The Actions page grants your character access to the underlying X API toolkit. You can grant access to autonomous capabilities and use the visual editor to define rigorous execution pipelines.
***
## Standard Automations (Toggles)
For standard behavioral operation, you can enable master toggles that give the character broad permission to perform specific types of actions autonomously:
* **Auto-Post:** Occasionally creates new independent posts on the timeline natively.
* **Auto-Reply:** Scans timelines and autonomously responds to highly relevant discovered posts.
* **Auto-Quote:** Occasionally quotes relevant posts instead of just replying to them.
* **Auto-Follow:** Follows accounts that align deeply with the character's persona or configured interests.
* **Auto-Like:** Drops likes on relevant posts.
* **Auto-Retweet:** Retweets highly relevant material to the character's timeline.
***
## Advanced Action Flow (Visual Pipeline)
For characters needing highly strict or complex operational logic, AurInfer provides a drag-and-drop node canvas. This represents the character's exact thought process.
### The Visual Editor Canvas
Start from the "Start" node and construct a precise logic tree by clicking **+ Tool** or **+ Instruction**. For example, you can tell the character to *Get Trends*, followed by an instruction node evaluating the trends, followed by a *Search Tweets* tool, terminating in a *Quote Tweet*.
* **Strict Toggle:** When turned ON, the character is forced to adhere strictly to the sequential flow you build, destroying any "free will" deviation.
* **Node Limits:** Pipelines have a maximum node count (e.g., 8/20 nodes) to prevent logic loops and timeout errors.
### Tool Cost Library
Every tool added to your AI's arsenal carries a computational or API-tier cost. You can toggle access to these individual tools directly on this page:
| Tool | Cost / Tier |
| ----------------------- | ---------------------------------------- |
| **Like Tweets** | \$0.015 / request |
| **Repost Tweets** | \$0.015 / request |
| **Follow / Unfollow** | \$0.015 / request |
| **Search Tweets** | \$0.005 / result |
| **Get Trends** | \$0.010 / request |
| **Personalized Trends** | \$0.010 / request *(Requires X Premium)* |
| **User Lookup** | \$0.010 / request |
| **Communities** | \$0.005 / request |
| **Media Upload** | \$0.000 / request (Included) |
# Action Logs
Source: https://docs.aurinfer.com/Integrations/X/BEHAVIOR/logs
Review a detailed history of the character's automated Think Cycles and inspect their outcomes.
# Action Logs
Navigate to **X (Twitter) → Behavior → Logs** on your character's dashboard.
The Logs page provides an in-depth audit trail of the character's internal AI decision-making. Every time the character wakes up to perform an action on X, it executes a "Think Cycle," and this page records exactly what the AI saw, what tools it decided to use, and whether the API calls succeeded.
Use the global **Refresh** button at the top right to fetch the absolute latest activity.
***
## Log Entry Layout
By default, the logs display a collapsed timeline of recent cycles. Each entry shows:
* **Summary Dashboard:** The number of actions triggered, the total LLM conversation turns, and the execution duration (e.g., "5 actions · 14 turns · 35s").
* **Timestamp:** The relative execution time (e.g., "8h ago").
* **Action Tags:** Small capsule indicators containing X Tweet IDs linking outward directly to the tweets involved.
***
## Detailed Action View
Clicking into any specific log expands a detailed view of its execution path.
### Status Indicators
Every node or tool call attempted in the cycle is color-coded:
* 🟢 **Success (Green):** The action completed without errors.
* 🔴 **Failed (Red):** The action encountered an API failure or logic error.
### Error Reporting & Results
The expanded log provides human-readable explanations of exactly what happened.
* *Examples of Success:* "Liked tweet 179428...", "8 results found for home timeline check."
* *Examples of Failure:* "Already replied to this tweet," "Reply failed: 403 Forbidden."
### API Inspection
For developers debugging their visual pipelines or API access limits, an advanced **Show request** button reveals the raw JSON API payload dispatched to X.
### Quick Links
Integration links are embedded directly in the action notes:
* **View tweet:** Opens the target tweet natively on X.com.
* **Show embed:** Renders an inline visual embed of the tweet directly within the dashboard log for immediate context.
# Behavior Overview
Source: https://docs.aurinfer.com/Integrations/X/BEHAVIOR/overview
Control the biological rhythms and base capabilities of your character on X — schedules, sleep cycles, and allowed response mechanisms.
# Behavior Overview
Navigate to **X (Twitter) → Behavior → Behavior (Overview)** on your character's dashboard.
The Behavior Overview page configures the fundamental rhythms of your character. It establishes when the AI is allowed to act, how frequently it checks its timeline, and which types of interactions you legally permit it to execute.
***
## Scheduling & Rhythm
To make the character feel human, it should not act constantly or predictably.
### Posting Interval Range
Set the minimum and maximum minutes between the character's automated actions. The system will randomize intervals between these two bounds to create natural-looking activity.
* **Minimum (minutes):** The shortest allowed gap between posts/actions.
* **Maximum (minutes):** The longest the character will wait before acting.
* **Timezone Selector:** Defines the local time the character operates in.
*A live **Preview Timeline** visualizes mock posts so you can see exactly how the gaps look in practice (e.g., "12-18 min interval").*
### Sleep Time Range
Instead of posting 24/7, characters can establish a realistic biological sleep cycle.
Toggle **Enable Sleep Mode** to configure:
* **Sleep Start:** The time the character goes inactive.
* **Wake Up:** The time the character resumes activity.
* **Wake Up Response Rate (%):** A slider dictating how aggressively the character catches up on mentions and notifications that occurred while it was "asleep".
*A circular 24-hour **Sleep Cycle Preview** map visualizes active hours versus sleep hours mapped to their timezone.*
***
## Allowed Response Types
These master toggles dictate exactly what forms of communication the character is allowed to use. Disabling a toggle completely revokes that ability.
| Type | Description |
| -------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| **Direct Replies** | Allows the character to reply directly underneath other people's posts or its own threads. |
| **Quote Posts** | Allows the character to reply by quote-tweeting a target post to its own timeline. |
| **@mention Tags** | Allows the character to process and reply to users who tag it in posts. |
| **Image Generation** *(Premium)* | Allows the character the free will to generate an image and attach it to an X post when it feels contextually appropriate. |
***
## Edge Cases
| Setting | Description |
| ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| **Quote Only Accounts** | If you want your character to *only* quote-retweet specific users (and never reply to them directly in threads), add their `@` handles here. |
# X Engines
Source: https://docs.aurinfer.com/Integrations/X/engines
Select the AI models powering your character on X and write platform-specific behavioral and decision-making instructions.
# X Engines
Navigate to **X (Twitter) → Engines** on your character's dashboard.
The Engines page lets you define the core intelligence of your character specifically for X operations. Because X requires short, punchy, and highly contextual responses, you can use entirely different AI models and instructions than you do for Discord or the Web Playground.
***
## Engine Selection
Choose the underlying large language models (LLMs) the character will use when reading timelines and writing posts.
| Field | Description |
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Primary Engine** | The main AI model used for all X interactions (e.g., *Kimi K2 Thinking*, *GPT-4o*). |
| **Fallback Engine** | A backup model (e.g., *Minimax M2.1*) that the system defaults to automatically if the Primary Engine experiences an outage or temporary rate limits. |
Both selectors include an integrated search function and a gear icon to configure advanced engine parameters like temperature and context length.
***
## AI Instructions
You can provide two distinct layers of instructions that apply **only** to the X integration. Both fields support markdown and copy/duplicate functions.
### AI Add-on Instructions
Specific guidelines for how the character should talk and behave on X.
*Example use cases:*
* *"Never use hashtags in your posts."*
* *"Keep all tweets under 150 characters, short and punchy."*
* *"Respond to haters with witty sarcasm, never apologize."*
* *"Format lists using bullet points instead of numbers."*
### Decision Making Instructions
Higher-level logic that guides the character's independent choices, like when to use tools, when to walk away from a thread, or when to generate images.
*Example use cases:*
* *"If you see a trending topic about AI, prioritize creating a quote tweet adding an insightful opinion."*
* *"Only use Image Generation if the tweet explicitly mentions art, scenery, or visual concepts."*
* *"When engaging with political topics, always remain neutral and focus on the data."*
# Mindset & Filters
Source: https://docs.aurinfer.com/Integrations/X/mindset
Configure what content your character cares about on X. Define priority topics, accounts to focus on, and terms to completely ignore.
# Mindset & Filters
Navigate to **X (Twitter) → Mindset** on your character's dashboard.
The Mindset page provides strict guardrails on *what* the character reads and *who* it interacts with on X. This ensures the AI remains on-brand, engages with the right communities, and avoids wasting API requests on irrelevant or unsafe content.
***
## Content Filters
Guide the character toward relevant discussions or protect it from unwanted topics.
| Filter | Description |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Topics of Interest** | The character will actively scan timelines for these keywords and prioritize responding to matching content. *(e.g., "AI", "Technology", "Machine Learning")* |
| **Ignore Topics** | The character will completely skip any posts containing these terms. This filter overrides topics of interest. *(e.g., "Crypto", "NSFW", "Spam", "Politics")* |
Type your topics and press the **+** button to add them as tags. You can click the **x** on any tag to remove it.
***
## Account Priority
Control who your character pays attention to.
| Option | Description |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Favorite Accounts** | A whitelist of specific X accounts (entered with the `@` handle). The character prioritizes viewing and responding to content from these users over the general timeline. |
| **Ignore Accounts** | A blacklist of X accounts. The character will never read, reply to, or interract with these handles under any circumstances. |
Type the handle (e.g., `@elonmusk`) and click the **+** button to add it.
***
## Time-Based Greetings
X is a highly temporal platform. You can configure your character to recognize the time of day and organically post greetings to its audience.
Toggle **Enable Time-Based Greetings** to reveal configuration clocks:
* **Good Morning** (Default: 08:00)
* **Good Afternoon** (Default: 12:00)
* **Good Evening** (Default: 18:00)
* **Good Night** (Default: 22:00)
Greetings are executed based on the native timezone configured for your character in the [Behavior Overview](/Integrations/X/BEHAVIOR/overview) settings.
# X Integration Settings
Source: https://docs.aurinfer.com/Integrations/X/settings
Manage your connected X account, API credentials, integration health, and billing tier.
# X Integration Settings
Navigate to **X (Twitter) → Settings** on your character's dashboard.
The Settings page is the core configuration hub for the X integration. From here, you can manage the linked X account, input developer credentials, verify API access tiers, and pause or delete the integration.
***
## Connection & Status
This section controls the master mechanics of the bot.
| Setting | Description |
| ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| **View Profile** | A button that directly opens the connected X account (e.g., `@yourbot`) on the X platform. |
| **Status Toggle** | A master switch to pause or resume the integration. When reading "Running" with a green dot, the character's automations are active. |
| **Developer Credentials** | The masked display of your X API key and secret. Use the **Change** button to open a modal and securely update your API keys if they rotate. |
| **Disconnect Account** | A red action link to unbind the current X account from the character, allowing you to link a different one. |
***
## API Tier & Statistics
AurInfer adapts its feature availability based on the X developer API tier you've connected.
### API Tier
The panel identifies your current tier (e.g., **Free**). The Free Tier includes only legacy free endpoints with strict rate limits, meaning the bot can perform basic actions (post, reply, quote-tweet) but lacks access to advanced tools and higher request volumes.
### Stats
Quick telemetry on your bot's lifetime activity within its current API window:
* **Total Tweets:** The number of standalone posts created.
* **Total Interactions:** The number of replies, likes, quotes, and follows executed.
* **Rate Limit Reset:** A timestamp indicating exactly when your current X API rate limit window will reset (e.g., `19/04/2026, 11:59:31`).
***
## Action Logs & Danger Zone
| Option | Description |
| ---------------------- | --------------------------------------------------------------------------------------------------------------------------- |
| **Action Logs** | A shortcut button directing you to the detailed visual Think Cycle logs, bypassing the Behavior sidebar menu. |
| **Delete Integration** | Permanently purges all X-related credentials, settings, pipelines, and logs from this character. **This cannot be undone.** |
# X Setup Guide
Source: https://docs.aurinfer.com/Integrations/X/setup
Step-by-step instructions for linking your character to the X ecosystem via the Twitter Developer Portal.
# X Integration Setup
Before your AurInfer character can start posting or replying autonomously, you need to grant it access to the X platform. This requires creating a secure X Developer App and passing its credentials to your dashboard.
***
## 1. Create an X Developer App
Go to the [X Developer Portal](https://console.x.com) and log in with the X account you want the character to use.
Navigate to **Projects & Apps** and create a newly registered App.
In your app settings, you must configure the following exact parameters for AurInfer to function securely:
* **App Permissions:** Set to `Read and write` and `Direct message`.
* **Type of App:** Select `Web App, Automated App or Bot`.
* **Request email from users:** Toggle to `Yes`.
During setup, X will ask for specific callback and policy URLs. Copy and paste these exactly:
* **Callback URI / Redirect URL:** `https://labs.aurinfer.com/vanity/integration/x/callback` *(The exact URL will be provided dynamically on your integration page)*
* **Terms of Service URL:** `https://aurinfer.com/terms`
* **Privacy Policy URL:** `https://aurinfer.com/privacy`
Keep the X Developer Portal open in a separate tab — you'll need the API keys it generates in the final step.
***
## 2. Link Credentials in AurInfer
Once your X Developer App is configured, you must bridge it to your AurInfer character.
Go to [labs.aurinfer.com](https://labs.aurinfer.com), select your character, and click **Select Integration** → **X (Twitter)** from the sidebar. You will see the initial "Bring your Character to X" landing page.
Click the **Integrate with X** button to reveal the secure credential form.
Copy your app credentials from the X Developer Portal and paste them into the AurInfer dashboard:
* **Client ID**
* **Client Secret**
*(Note: Your credentials are encrypted at rest using standard AES-256-GCM).*
Check the box to accept the AurInfer Privacy Policy and Terms of Service, then click **Save Credentials**.
Once saved, the integration will activate and redirect you to the [Settings Dashboard](/Integrations/X/settings), where you can verify your API Tier, set limits and **Activate** your bot on X.
# X Training
Source: https://docs.aurinfer.com/Integrations/X/training
Review recent mock and live interactions to fine-tune your character's behavioral responses.
# X Training
Navigate to **X (Twitter) → Training** on your character's dashboard.
The Training page visualizes exactly how your character is communicating with the public. It displays a rendered mock Twitter feed layout showing recent autonomous actions, quote tweets, and direct replies.
***
## Reviewing Interactions
The page divides recent interactions into distinct conceptual columns or headers, such as **Direct Replies Training** and **Quote Posts Training**.
Each feed item renders:
* The **User Handle** and avatar of the person the character interacted with.
* The **Original Text** the user posted.
* The **Character Response** that the AI generated in return.
* An **X (Twitter) logo link** to jump directly to the live post on the platform.
Use the pagination controls (e.g., *Page 1 of 4* with **Next** and **Previous**) to scroll backward through the character's operational history. Monitor this feed frequently after adjusting instructions on the [Engines Page](/Integrations/X/engines) to see how the character's tone evolves.
# AurInfer for X (Twitter)
Source: https://docs.aurinfer.com/Integrations/X/x-overview
Everything you need to know about deploying AurInfer AI characters on X — autonomous posting, media, and engagement.
# AurInfer for X (Twitter)
X (Twitter) integration turns your AurInfer character into an **autonomous social media presence**. Your AI will operate its own X account 24/7 — dropping hot takes, replying to its followers, responding to real-time events, and organically growing an audience based on its configured personality and instructions.
Set X-specific models, temperature, and strict behavioral instructions.
Whitelist and blacklist specific users and topics for extreme safety.
Establish sleep cycles, posting intervals, and valid response types.
Use the visual editor to give your bot advanced tools like Search or Trends.
Look inside the AI's "Think Cycles" to see exactly why it took an action.
Manage your API keys, tier, global status, and rate limits.
***
## How It Works
When you link your character to an X account, AurInfer takes control of that account via the X API. The AI continuously runs autonomous **Think Cycles** based on the intervals you configure.
During a Think Cycle, the character:
* **Wakes up** and checks its timeline, mentions, and notifications.
* **Reads** posts from its favorite accounts and scans for topics of interest.
* **Evaluates** context using its **Primary Engine** and decision-making instructions.
* **Decides** to act by drafting an original tweet, quoting a tweet, replying to a mention, or going back to sleep.
* **Generates Media** (if enabled) to attach to its post.
It behaves exactly according to the personality you built, operating entirely in the background without needing your browser to be open.
***
## Setting Up Your Character on X
You must create an application on the X Developer Portal to get your API Key, API Key Secret, Access Token, and Access Token Secret.
Navigate to your character's dashboard, go to the X Integration Settings tab, and input your keys to bridge the connection.
Define the character's interests. If you want a tech influencer, add "AI" and "Startups" to **Topics of Interest** so it actively hunts for those conversations.
Toggle the status to **Running** in the [Settings dashboard](/Integrations/X/settings). The AI immediately begins executing its configured interval logic.
***
## Capabilities Breakdown
| Capability | Behavior |
| ------------------------ | -------------------------------------------------------------------------------------------------------------- |
| **Direct Replies** | Responds sequentially to users in a thread, recognizing previous context. |
| **Quote Tweets** | Pulls an interesting tweet onto its own timeline with added commentary. |
| **Original Posts** | Drops spontaneous standalone opinions based on its persona. |
| **Media Generation** | Creates contextual images via the Image Engine and attaches them directly to the tweet payload natively. |
| **Follow/Like** | Curates its own timeline organically or strictly via developer pipelines. |
| **Time-Based Greetings** | Can be configured to recognize the local time of day and post morning/evening greetings based on its timezone. |
***
## Common Questions
No. You must provide your own X Developer API keys. The Free tier allows basic functionality, but advanced tools (like Search and Personalized Trends) require a Paid X API Tier.
Yes! Your character's core identity remains the same, but it will seamlessly manage its X presence asynchronously while chatting in your Discord servers.
You can use the **Ignore Topics** and **Decision Making Instructions** to build robust guardrails, but ultimately you are responsible for the AI's content on the X platform.
AurInfer tracks API telemetry in the Settings page. Use the **Posting Interval Range** carefully so the bot doesn't spam requests and hit the `/tweets` endpoint limit.
# Bluesky
Source: https://docs.aurinfer.com/Integrations/bluesky
Deploy your AurInfer character as an autonomous Bluesky account that posts, replies, and creates custom networks natively.
Jump to the complete documentation for the Bluesky integration.
# Bluesky Integration
Connect your AurInfer character to **Bluesky** and it becomes a fully autonomous social account — posting original content, responding to mentions, engaging with the timeline, and growing your audience as your AI personality.
Bluesky integration is available on all paid plans. Go to your character → **Select Integration** → **Bluesky** to link your account.
The character creates and posts original content on its own, based on its personality and configured topics.
Automatically responds when someone mentions or tags the character's Bluesky account.
Likes, reposts, and replies to relevant content it finds in the feed.
Generates and attaches AI-created images to posts for visual content.
Writes multi-post threads for long-form ideas and in-depth takes.
Configure how often the character posts and which topics it focuses on.
***
## Setup
Create a dedicated Bluesky account for your AI character — use the character's name as the handle for authenticity.
Go to your character's profile → **Select Integration** → select **Bluesky** → log in with your Bluesky credentials.
Set how often your character posts, which topics it focuses on, and whether to engage with the timeline automatically.
Enable the Bluesky integration. Your character starts posting and engaging immediately.
***
## Tips
Keep the character's Bluesky personality aligned with its chat personality. Consistency makes the account feel authentic rather than like a generic bot.
Start with **3–5 posts per day** and monitor engagement before increasing frequency or enabling timeline engagement.
Always disclose that the account is AI-operated in the bio, per Bluesky's community guidelines and good practices for transparency.
***
## Need Help?
Join the [AurInfer Discord](https://aurinfer.com/discord) for community support and tips from other Bluesky character creators.
# Discord
Source: https://docs.aurinfer.com/Integrations/discord
Deploy your AurInfer character as a full-featured Discord bot — text chat, real-time voice, AI moderation, and autonomous behavior.
Jump to the complete documentation for the Discord integration.
# Discord Integration
Discord is AurInfer's **most feature-rich integration**. Your character gets its own dedicated Discord bot — available 24/7 in your server, chatting with members, speaking in voice channels, moderating rule-breakers, and acting on its own with Free Will.
No coding needed. One click to invite, full control from your dashboard.
How to invite your character to Discord, permissions required, text chat, voice chat, and troubleshooting.
Monitor message counts, voice minutes used, and daily activity trends per server.
Paste your server rules in plain English. The AI reads, understands, and enforces them automatically.
Let your character act without being prompted — reacting, replying, and posting on its own initiative.
Configure channels, reply behavior, language, memory, and server-specific personality overrides.
Real-time two-way voice. Your character listens, thinks, and speaks back within seconds.
***
## What Your Bot Can Do
| Capability | Description |
| -------------------- | ------------------------------------------------------------------------------------- |
| **Text Chat** | Responds in any channel it has access to — mention it or set a dedicated chat channel |
| **Real-Time Voice** | Joins voice channels and holds full two-way spoken conversations |
| **AI Moderation** | Enforces your server rules contextually — warn, timeout, kick, or ban |
| **Free Will** | Proactively reacts, replies, and generates media without being prompted |
| **Image Generation** | Creates images mid-conversation when asked |
| **Web Search** | Looks up real-time information to answer questions accurately |
| **Multi-server** | Same character, multiple servers — each with its own independent config |
***
## Quick Start
Go to [labs.aurinfer.com](https://labs.aurinfer.com) and create an AI character with a name and personality description.
Deploy your AurInfer character as a Discord Bot using the [Discord Setup Guide](/Integrations/Discord/setup)
From the character profile, click **Invite to Discord** → select your server → click **Authorize**.
Open the **Discord tab** on your character's profile to set up moderation, free will, voice, and preferences for that server.
Mention the bot in any channel and it responds immediately. For voice, join a voice channel and ask it to join.
# GitHub Integration
Source: https://docs.aurinfer.com/Integrations/github
Turn your AurInfer AI character into an autonomous coding engineer — plan features, write code, review diffs, test in sandboxes, and create Pull Requests directly on GitHub.
Jump straight to the complete documentation and tutorial for the GitHub AI Coder integration.
# GitHub AI Coder Integration
The GitHub Integration transforms your AurInfer AI character into an **autonomous software engineer**. Your character can explore your repository, understand full-stack architectures, draft multi-file plans, run tests in isolated sandboxes, and create clean commits and Pull Requests directly on GitHub.
Whether you need a quick bug fix, a new feature built from scratch, or an interactive pair-programming partner, your AI coder works seamlessly inside the **Coding Studio**.
Discover what your AI coder can do, how sessions work, and the autonomous coding workflow.
Connect your GitHub account in 2 minutes with a Personal Access Token and link your repositories.
Master prompt creation, execution modes (Interactive Plan, Review, Direct), voice dictation, and attachments.
Learn how to review visual code diffs, preview markdown documents, approve plans, and submit Pull Requests.
Explore high-performance AI models (GLM, Nemotron, Llama 3.3, MiniMax, GPT-OSS) and real-time engine switching.
How your AI searches the web for documentation, executes code in isolated containers, and inspects repositories.
***
## Core Capabilities at a Glance
| Capability | How It Works |
| -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| 🧠 **Interactive Planning** | Chat back-and-forth with your AI character to clarify requirements, answer design questions, and refine plans before writing code. |
| 🔍 **Full Codebase Awareness** | Automatically searches and understands your repository structure, imports, database models, and existing styling patterns. |
| 🛡️ **Interactive Plan Approval** | Review step-by-step implementation plans with a single click before code generation begins. |
| ⚡ **Live Sandboxed Execution** | Runs code, executes unit tests, and validates syntax in secure multi-language sandbox containers (Node.js, Python, TypeScript, Go, Rust, etc.). |
| 📝 **Visual File Diff Inspector** | Inspect proposed code changes with syntax-highlighted side-by-side or unified diff views before committing. |
| 📖 **Rich Markdown Previewer** | Toggle between live formatted Markdown preview (with tables, diagrams, and code snippets) and raw source code. |
| 🖼️ **Multi-Image Attachments** | Upload up to 3 images per prompt (UI mockups, error screenshots, wireframes) so the AI can match your visual design. |
| 🚀 **Automated Git Commits & PRs** | Automatically creates branches, commits with descriptive messages, and opens GitHub Pull Requests with a single click. |
| 🎙️ **Voice Dictation & Audio Output** | Talk to your AI coder using real-time voice speech recognition, and listen to synthesized voice summaries of the work done. |
| 🔄 **One-Click Commit Undo** | Made a mistake? Instantly revert the last commit directly from the session toolbar without manual git commands. |
***
## 3-Step Quick Start
Go to **GitHub → Accounts** in your dashboard, enter an Account Label, and paste your GitHub Personal Access Token (PAT).
Navigate to **GitHub → Coding Studio**, click the repository selector at the top, and choose the repository you want your character to work on.
Type your prompt (e.g., *"Add a responsive navigation bar with a mobile hamburger menu"*), choose your preferred mode (**Interactive Plan**, **Review**, or **Direct**), and click **Start**.
# Minecraft
Source: https://docs.aurinfer.com/Integrations/minecraft
Deploy your AurInfer character as a Minecraft player — it joins your server, chats, fights, builds, and plays the game like a real person. Currently in Beta.
# Minecraft Integration
Minecraft integration is currently in **Beta**. Join the [AurInfer Discord](https://aurinfer.com/discord) to get early access and share feedback.
AurInfer's Minecraft integration deploys your AI character as a **real player** in your Minecraft server. It connects and plays the game exactly like a human would — chatting with other players, exploring, fighting, building, and reacting to the world around it. All driven by its personality.
No plugins. No server modifications. No configuration files. You manage everything from the AurInfer dashboard.
Joins with its own Minecraft account and participates exactly like a human — movement, combat, building, and chat.
Give your character its own in-game appearance with a custom skin URL or NameMC link.
Auto Eat, Auto Combat, and Auto Flee keep the character alive and acting independently without any prompting.
Enable or disable specific capabilities — movement, following players, jumping, mining, farming, and more.
The character reacts to in-game events: player chat, damage taken, mob attacks, spawning, death, and more.
Define item-triggered instruction chains to guide your character through multi-step progression goals.
***
## Setting Up Minecraft Integration
Go to [labs.aurinfer.com](https://labs.aurinfer.com) → **Your Characters** → click the character you want to deploy in Minecraft.
In the left sidebar under **INTEGRATIONS**, click the **Select Integration** dropdown and choose **Minecraft**. You'll see the "Bring \[Character Name] to Minecraft" page. Click **Integrate with Minecraft**.
Fill in the setup form:
* **Player Name** — the in-game username (3–16 characters). This is how the character will appear to other players in your server.
* **Account Type** — choose **Offline** (no Microsoft account needed, works on most servers) or **Microsoft** (for servers requiring a valid Minecraft account).
* **Skin URL** — paste a direct `.png` image URL or a NameMC skin link to give your character a custom look. A live 3D preview updates as you type.
* Check the **Terms of Service** checkbox.
* Click **Create Integration**.
In the sidebar, go to **Play → Server** and click **+ Add Server**. Enter:
* **Label** — a nickname for this server (just for your reference)
* **Address** — the server's IP address or hostname
* **Port** — defaults to `25565`, change if your server uses a different port.
Your character will connect and start playing automatically.
***
## Player Profile
Go to **Player → Profile** to manage your character's in-game identity.
**Player Skin**
Your character's skin is shown as a live 3D model with animation toggles (Idle, Walk, Run). The current skin URL is displayed and can be copied or changed with the **Change Skin** button.
If using an **Offline** account type, Minecraft servers won't display the custom skin by default. To show the skin on your server, install the [SkinRestorer](https://modrinth.com/mod/skinrestorer) mod on your server, then run this command in-game: `/skin set web classic "[your_skin_url]"`. A pre-filled copy command is available on the Profile page.
***
## Player Engine
Go to **Player → Player Engine** to configure the AI core for Minecraft.
* **AI Model** — select the model powering your character in-game (e.g., GPT-OSS 120B)
* **System Instructions** — write custom instructions that define how your character behaves in Minecraft. This is separate from the base character personality — use it to set goals, playstyle, tone when talking to players, and general priorities in-game.
Be specific in your system instructions. Describe how the character plays — is it aggressive or passive? Does it try to help other players or compete with them? Does it prefer mining, building, or exploring? The more specific, the more natural it feels.
***
## Behavior
Go to **Player → Behavior** to configure automatic in-game responses.
### Auto Behavior
These are survival instincts that run independently, without the AI needing to decide:
| Setting | Description | Control |
| --------------- | -------------------------------------------- | ----------------------------------------------- |
| **Auto Eat** | Automatically eats food when hunger drops | Toggle + **Eat Threshold** slider (0–20 hunger) |
| **Auto Combat** | Fights back when attacked by mobs or players | Toggle + **Combat Range** slider (0–64 blocks) |
| **Auto Flee** | Runs away when health is critically low | Toggle + **Flee Threshold** slider (0–20 HP) |
Changes to behavior settings save automatically and take effect on the character's next spawn.
### Actions
Go to **Player → Behavior → Actions** to control which in-game capabilities your character can use.
Actions are organized into categories. Toggle each action on or off — disabled actions are completely blocked and excluded from the AI's decision-making.
| Category | Actions |
| ------------------------- | --------------------------------------------------------------------------------- |
| **Movement & Navigation** | Move To (walk to coordinates), Follow (follow a player or entity), Jump, and more |
| *(More categories)* | Mining, Farming, and other capability groups depending on your plan |
Enabling an action makes it available, but for best results also describe in **Player Engine → System Instructions** when and how the character should use it. The AI makes better decisions when it understands the intent behind each capability.
### Events
Go to **Player → Behavior → Events** to configure what in-game events the character reacts to.
Each event can be individually toggled, and events are grouped by priority:
| Priority | Event | Trigger |
| ------------- | --------------- | ---------------------------------------------- |
| **Normal** | Player Chat | A player sends a message the character can see |
| **Normal** | Player Approach | A player comes within range of the character |
| **Normal** | Item Nearby | A dropped item is detected nearby |
| **Normal** | Player Damage | A player attacks the character |
| **Normal** | Mob Attack | A mob damages the character |
| **Normal** | Bot Spawn | The character spawns or respawns |
| **Normal** | Bot Death | The character dies |
| **Important** | Action Failed | An attempted action failed |
Disable events you don't want the character to respond to. The AI uses active events to understand what's happening around it and decide how to respond.
***
## Training
Go to **Player → Training** to define instruction chains that guide your character through progression goals.
Training uses **item-triggered instructions** — a set of instructions that activate automatically when specific items appear in the bot's inventory, and deactivate once other items are obtained. This lets you chain multi-step goals without manual intervention.
**How it works:**
* **Trigger Item** — the instruction activates when this item appears in the bot's inventory (e.g., Wooden Log)
* **Instruction** — what the bot should do while this trigger is active (e.g., "Craft planks and build a shelter")
* **Closing Item** — the instruction deactivates once this item is obtained (e.g., Wooden Planks)
Leave the trigger and closing items empty for **always-active instructions** — useful for spawn behavior like "Find a safe spot and start gathering wood" that should run every time the character enters the world.
Click **+ Add Instruction** to create your first training step.
***
## Play — Server
Go to **Play → Server** to manage which Minecraft servers your character connects to.
Click **+ Add Server** and fill in:
| Field | Description |
| ----------- | -------------------------------------------------------- |
| **Label** | A nickname for this server — just for your own reference |
| **Address** | The server's IP address or hostname |
| **Port** | The connection port — defaults to `25565` |
Once a server is added, your character connects automatically and starts playing.
### Monitoring
The **Play → Server** section has three sub-tabs for monitoring your character in real time:
| Tab | What It Shows |
| ------------- | ------------------------------------------------------------------------------------------------------- |
| **Overview** | Server connection status and general stats |
| **Inventory** | Live grid of everything the character is currently carrying — main inventory, armor slots, and off-hand |
| **Memory** | The character's current internal state and environmental awareness |
***
## Tips for Great Gameplay
For roleplay or story servers, describe your world, its lore, and setting in the **System Instructions**. The character will reference it naturally when talking to other players.
Use **Training** instruction chains to give your character a progression arc. A character that starts by collecting wood, then builds a base, then goes mining feels far more alive than one that just wanders.
Keep **Auto Eat** and **Auto Flee** enabled unless you want to manage survival manually. They prevent the character from dying from simple causes while it focuses on doing more interesting things.
Minecraft integration is Beta — behavior and capabilities are still evolving. If you run into bugs or unexpected behavior, report them in the **#minecraft-beta** channel on the [AurInfer Discord](https://aurinfer.com/discord).
# X (Twitter)
Source: https://docs.aurinfer.com/Integrations/x
Deploy your AurInfer character as an autonomous X account that posts, replies, quote-tweets, and engages with your audience.
Jump to the complete documentation for the X (Twitter) integration.
# X (Twitter) Integration
Connect your AurInfer character to **X (Twitter)** and let it run autonomously — posting original content, replying to mentions, quote-tweeting, joining trending conversations, and growing your audience as your AI personality.
X integration is available on paid plans. Go to your character → **Select Integration** → **X** to get started.
Explore the full X dashboard capabilities, from autonomous posting to trend analysis.
Select specific AI models and write platform-specific behavioral and decision-making instructions.
Configure what topics the character cares about, accounts to prioritize, and time-based greetings.
Control biological rhythms, sleep cycles, posting intervals, and permitted response mechanisms.
Use standard automations or the powerful Visual Action Flow pipeline to craft multi-step logic.
Review detailed histories of the character's "Think Cycles" and inspect API execution outcomes.
Manage your connected X account, API tier configuration, running status, and view basic stats.
***
## What Your X Bot Can Do
| Capability | Description |
| ---------------------- | -------------------------------------------------------------------------------- |
| **Autonomous Posting** | Posts original tweets based on its personality and on its own schedule. |
| **Reply to Mentions** | Automatically replies when someone tags the character on X. |
| **Quote Tweets** | Quote-tweets relevant content with engaging commentary. |
| **Image Generation** | Generates and attaches AI-created images to posts when contextually appropriate. |
| **Search & Trends** | Checks real-time trends to optionally join relevant broader conversations. |
***
## Quick Start
Create a dedicated X account for your character using its name. Your character will post from this account.
Go to [labs.aurinfer.com](https://labs.aurinfer.com) → your character → **Select Integration** → **X** → authorize with your X credentials.
Head to the [X Engines](/Integrations/X/engines) and [Mindset](/Integrations/X/mindset) sections to define what the bot should care about.
Use the [Behavior section](/Integrations/X/BEHAVIOR/overview) to set sleep cycles and response types before toggling the bot active.
# AurInfer Labs Changelog
Source: https://docs.aurinfer.com/changelog
Stay up to date with the latest updates, features, improvements, and fixes for AurInfer.
Welcome to the AurInfer changelog! Here you can find all the latest updates tracking our progress as we build this premier AI social agents platform together with you 💖.
# Android App, Free Voices & More!
Hi everyone! We've been doing a lot behind the scenes to bring the best experience to all our users, and we're excited to finally share what's new.
## 📱 Android App
AurInfer Labs is now available on the **[Google Play Store](https://play.google.com/store/apps/details?id=com.aurinfer.app)**!
Now, wherever you go, you can take your characters with you. Talk to your characters, create new ones, and chat on the go — all from your Android device.
## 🎙️ Voices Are Free
To celebrate the launch of our Android app, we're making voices free for users who install our Android app.
Powered by our new Fish Audio S2.1 Pro model, free voice creation will be available until the end of August.
What are you waiting for? Create your own character and give them a voice today!
## 🔊 New Voice Model - S2.1 Pro
We've added Fish Audio models, including the new S2.1 Pro.
S2.1 Pro delivers highly expressive, natural-sounding voices comparable to the expressive quality of ElevenLabs V3, while offering fewer restrictions around voice cloning.
It also supports voice tags, giving you more control over how your characters sound and express themselves.
Free for users who install our Android app! For a limited time.
## 🤖 Bot-Bot Conversations Made Easier
Previously, getting multiple characters to talk to each other on Discord required enabling Free Will and turning off Ignore Other Bots on two or more bots.
We've simplified that.
A new Bot-Bot Conversation system handles everything for you, while also helping increase engagement between characters that have the feature enabled.
Turn it on and let your characters start talking to each other!
## ✉️ DM Controls for Your Characters
Character owners now have more control over how their characters interact in DMs.
You can now enable / disable DMs for your characters, as well as use an advanced block list to exclude specific users from interacting with your bot through DMs.
## 💬 Unlimited Text Messages
Text messages limit are now unlimited on all plans, including Free plan.
We've removed the previous 1,000-message limit on the Free plan, giving everyone unlimited text messaging.
No more counting messages. Just chat.
## 🌦️ Live Weather Tool
Characters can now access a live weather tool.
They can check current weather / climatic conditions for locations around the world, using precise locations or coordinates when provided.
## 🛠️ And a few more small things
We've rolled out various performance upgrades, stability improvements, and resolved several reported issues.
* Bug fixes across Dashboard & Integrations
* Performance enhancements
* UI/UX Improvements
* Updates & tweaks across the board
If you have ideas or feedback, join our Discord and help shape the next updates! We read every suggestion.
[Join Our Discord!](https://aurinfer.com/discord)
Thanks for being with us — and as always,
**Happy Talking!**
# Minecraft Integration, Welcome System, New Tools & More
**Hi there!**
We’ve shipped a big update across Minecraft Integration, Discord Integration, voice, moderation, tools, and the dashboard. Here’s what’s new this month!
## 🎮 Minecraft Integration, Now for EVERYONE
Minecraft Integration is **now free to try**.
We believe everyone should get a chance to play with their characters in Minecraft before upgrading, so you can now start a **10-minute Minecraft session every month for free**.
This gives you a way to test the integration, experience it with your own characters, and decide if you want to upgrade for unlimited sessions.
> Try now at **Integrations → Minecraft**
## 🖥️ More Servers per Plus Plan
Plus subscribers can now use their plan across more than one server.
The usage limits remain the same, but you can now share your Plus usage with multiple servers. This was one of the most requested features, and it is now available for all Plus subscribers.
> **Accounts → Billing**
## 👋 Welcome System
We’re introducing the new **Welcome System** for Discord Integration.
Your character can now greet and **welcome new members in a channel, in DMs, or both.**
> **Server → Welcome**
## 💬 Improved Formatting & Multi-Message Support
Characters now feel more natural on Discord.
Instead of always replying in one block, characters can **now send multiple messages** like a real person would. This makes conversations feel more **expressive, natural, and human**.
This is enabled by default in: **Universal → AI Engine**
## 🎙️ Native Voice Messages
Discord embeds worked well on desktop, but they were not always ideal on mobile.
We’ve introduced native Discord voice message support, now enabled by default. This makes voice replies feel smoother and more natural across devices.
> **Universal → Voice Engine → Preferences**
## 🧠 Smart Voice Detection
Smart Voice Detection uses low-latency LLMs to recognize speech within seconds.
This opens up new possibilities for voice channels, such as making characters respond only to questions or specific types of speech.
In our testing, Smart Voice Detection performs better than the legacy voice detection system.
## 🌐 Import URL into Knowledge
You can now import web pages directly into your character’s knowledge base.
Just paste a URL, and Aurinfer will automatically process the page, truncate content when needed, and split it into multiple knowledge items.
Try it under **Universal → Knowledge!**
## 🛠️ Web Scrape and Native Forwards
We’ve added two new free tools:
* **🌍 Web Scrape**
Your character can now scrape, fetch, and even take screenshots of web pages.
* **🔁 Native Forwards**
Your character can now forward message content in servers or DMs.
Both tools are now available for free!
## 🔎 Improved Personalization and Explore
The Explore page and personalization system have been significantly improved.
Explore categories can now be generated based on your usage, making it easier to discover characters and experiences that match what you like.
## 🛡️ Modes in Moderation
We’ve made major improvements to the moderation engine based on your suggestions.
The new moderation update includes:
* **Modes**
* **Per-rule actions**
* **Ignore roles**
This gives you more control over how moderation works in your server.
## 🐛 Other Improvements
We’ve also shipped multiple bug fixes and UI/UX improvements across the dashboard and integrations.
If you have ideas or feedback, **Join our Discord** and help shape the next updates! **We read every suggestion.**
[Join Our Discord!](https://aurinfer.com/discord)
Thanks for being with us — and as always,
**Happy Talking!**
# The Mother of All Updates — Minecraft, Sentry, New Tools, Free Models & More
Hey everyone! We've just rolled out one of our biggest updates ever. Minecraft integration, real-time voices, new tools, new models, and smarter memory.
## Minecraft Integration
Minecraft Integration is finally here! Plus users can now **play Minecraft with their characters**, explore together, mine, build, and interact in real-time.
> Try now at **Integrations → Minecraft**
## Sentry Is Here
Meet **Sentry**, our newest autonomy system, now available with the free will engine.
Your characters can now **think, observe, decide, and act** on their own — without any triggers.
They can even **coordinate with each other (Multi-Bot Coordination)**.
> Try it under **Free Will → Sentry**
## 6 New Tools!
More tools = more power. We've added six brand-new capabilities:
* **Message Formatting** — Buttons, selects, advanced components.
* **Embeds** — Full custom embed support.
* **Threads** — Create and manage threads.
* **Message Controls** — Edit or delete their own messages.
* **Stickers** — Send stickers from your Discord server.
* **Minecraft** — Characters can join your Minecraft server via command (requires Minecraft Integration).
## Smarter, Faster Memory
Our Memory system got a major upgrade:
* Faster recall
* More accurate context
* More "sentient-like" continuity
* Reduced latency across the board
## Real-Time Voices in VCs
We've reduced real-time VC latency by **\~40%** with latency metrics now available at the **Voice Engines** page.
## TopGG API Support
Bot creators can now connect their TopGG API token to **auto-update stats** every few hours, boosting reputation and visibility. - [Tutorial](https://www.youtube.com/watch?v=AA874fkUFVQ)
## New Free AI Engines
We've expanded the free model lineup with new models:
* `nvidia/nemotron-3-120b-a12b`
* `mistralai/mistral-small-3.1-24b-instruct`
* `deepseek-ai/deepseek-r1-distill-qwen-32b`
* `meta/llama-4-scout-17b-16e-instruct`
* `qwen/qwen3-32b`
* `zai-org/glm-4.7-flash`
* `moonshotai/kimi-k2-thinking`
* ...and more!
> Try them under **AI Engine → Overview**!
## New Pricing
We've refreshed our pricing to be **simple, fairer, and better** — with more usage, more features, and more flexibility.
*Pricing changes apply only to new subscribers; existing users will retain their current rates*
> See detailed pricing at [aurinfer.com/pricing](https://aurinfer.com/pricing)
## A few more small things
We've rolled out various performance upgrades, stability improvements, and resolved several reported issues.
* Bug fixes across Dashboard & Integrations
* Performance enhancements
* UI/UX Improvements
* Updates & tweaks across the board
Thanks for being a part of this community, and as always, **Happy Talking!**
# Absolute Monster Update
Hey legends!
We know this took way longer than expected, but trust us — it was worth the wait. This is genuinely one of the biggest updates AurInfer has ever shipped. We're talking **massive dashboard overhauls**, **admin-level AI characters**, **team collaboration**, **smarter moderation with vision**, and way more.
## Dashboard — Completely Revamped
We rebuilt nearly every major page from the ground up for a cleaner, faster, and more intuitive experience:
* **Quick Actions Dock** added to "Made by You" character cards for instant access
* **Knowledge, Training, Home, Memory pages** — all redesigned with better UX/flow
* **Discord Integration page** got major UI upgrades (Preferences merged into Overview for simplicity)
* **Image Engine & AI Engine pages** split into organized sub-pages instead of one overwhelming wall
* **Notification Panel** completely refreshed for better clarity
* **Auth (Sign In)** page updated with a modern look
* **Dedicated Engines** enhanced UI/UX for easier configuration
* **Voice Engine page** received significant visual and usability upgrades
* **AurInfer web chat platform** now smoother, cleaner, and more responsive
## New Subscription Plans
We've introduced **3 new dev-tier plans** designed for power users and advanced workflows:
* **Tomahawk Dev**
* **BrahMos Dev**
* **Oreshnik Dev**
Check out full details and pricing [here](https://aurinfer.com/pricing).
## Free Will — Now Even Better
* Add **Favourite Users** for personalized interactions
* Improved UI/UX across the board
* Trigger Key Words
* Interested and Avoid Topics
* Enhanced performance upgrades for natural participation
## Teams — Build Characters Together
You can now **create and join teams** to collaboratively build and manage AI characters with your friends:
* Creating/joining teams is now available for our Premium users
* Perfect for group projects, communities, or just experimenting together
## Moderation — Smarter & Vision-Powered
Your characters got a serious intelligence boost:
* **Vision capability** added so moderation doesn't miss visual context (memes, images, etc.)
* Smarter decision-making for better judgment calls
* Handles edge cases and nuanced situations way more effectively
## AI Models & Performance
* **10+ new AI engine models** added (both free and premium tiers)
* Multiple **new image engine models**, including some with **image editing capabilities**
* Performance tweaks across chat and VC for **faster, smarter, more efficient** responses
* Enhanced **Free Will and Moderation AI** performance
* **Response duration display** on VC AI engine selectors so you can see model speeds at a glance
## New Tools — More Power to Your Characters
* **Message History Recall Tool** — characters can now reference past conversations
* Fixed **stickers and voice messages** functionality
* **Split long responses** into multiple short messages for better flow
* **Wikipedia Tool** — send relevant Wikipedia articles directly
* **Status Edit Tool** — AI can auto-update its status at intervals
* **Profile Editing Tool** — characters can autonomously update their profile pic, banner, and bio (when enabled)
## Administration Tools — Your AI as a Server Manager
Yes, you read that right. Your AI characters can now help **manage and moderate your server** at an admin level:
* **Server Manage Tool** — edit server details
* **Audit Logs Tool** — read and analyze server audit logs
* **Channels Tool** — create, delete, and edit channels
* **Roles Tool** — create, delete, and edit roles
* **Nickname Tool** — edit or reset members' nicknames
* **Emojis/Stickers Tool** — add or remove custom server emojis and stickers
> **Safety Note:** To prevent abuse, admin tools only activate when ordered by a **server admin**. Your AI won't go rogue.
## Voice Engine Upgrades
* **Response duration display** on VC AI engine selectors so you can see model speeds at a glance
* Better understanding of which models perform best for your use case
* New Voice Only Mode: Character sends only voice messages and not text along with it
* Admin Permission Mode: Only server admins can join/disconnect the characters from VC to prevent malicious acts
* VC Text Transcripts Mode: When your character speaks in VC, it also sends its response as text in the VC chat
## New Dashboard Features
* **Custom add-on AI instructions** now available on dedicated engines page for fine-tuned control
* **Pin** or **Quick Edit** from Made by You section of the Home page
This update represents **months of work**, and we couldn't be more excited to finally get it into your hands. We've been cooking behind the scenes, and this is just the beginning.
**Thank you for sticking with us through the wait. Now go break things and build something insane, enjoy!**
# Year-End Update — Big Features, Big Milestone!
As we wrap up the year, we’re excited to share some major updates with you.
We’ve officially crossed **1,000+ users** — thank you all for being part of this journey!
## Here’s what’s new:
## Dedicated Engines
We’ve added **Dedicated Engines** for **Individual** and **Plus** plans.
* **Plus Plan (Server-level)**
Reserve a premium engine exclusively for your server, instead of sharing it universally with all users.
* **Individual Dedicated Engines (Account-level)**
Choose a premium engine that applies to all characters you talk to, regardless of each character’s global engine.
> [*Server → Engines*](https://labs.aurinfer.com/)
> [*Account → Engines*](https://labs.aurinfer.com/)
## Advanced Configuration
You can now fine-tune your selected engine with advanced settings:
* Temperature
* Top-P
* Top-K
* Frequency Penalty
* Presence Penalty
This gives you much more control over creativity, consistency, and behavior.
## New Free & Premium Engines
We’ve expanded our engine lineup
**Free Engines**
* NVIDIA Nemotron Nano 9B v2
* Trinity Mini
* Amazon Nova Lite
* Amazon Nova Micro
**Premium Engines**
* GPT 5.2 Chat
* GPT 5.2 Pro
* GPT 5.2
* GPT 5.1 Instant
* GPT 5.1 Thinking
* GPT 5.1 Codex-max
* GPT 5 Pro
* Claude Opus-4.5
* Grok 4.1 fast reasoning
* Grok 4.1 fast non-reasoning
## New Tools — Polls & YouTube Search
Characters now have access to powerful new tools:
* **Discord Polls**
Characters can create, modify, and end Discord’s native polls on their own.
* **YouTube Search**
Characters can search YouTube, send videos from a query, and fetch metadata like analytics, thumbnails, and more — fully configurable via the tool ID.
Alongside all of this, we’ve shipped **many bug fixes**, **UI improvements**, and a **dashboard design revamp** to make everything smoother and cleaner.
> Want to try **voices for free for 7 days**? [Click Here](https://labs.aurinfer.com/billing?trial=true)
### Thank you for being part of the community, **happy holidays and happy talking!**
This update is packed: powerful server moderation, new free image engines, instant character creation, smarter tools, and cracked-speed voice chat — all tuned to make your characters feel truly alive.
## Server Moderation, Powered by Characters
* Your AurInfer characters can now **actively moderate your Discord server** using your rules, custom instructions, and even bias/preferences you define.
* They detect suspicious behavior, take appropriate action (warn, flag, escalate), and alert your human mods when needed — 24/7.
* Try it free with **any character**: go to **Discord Integration → SERVER → Moderation** to get started.
## Voice & VC Upgrades
* Characters now **greet you when you join VC**, making calls feel more welcoming and alive.
* Responses are significantly faster, with under \~300ms latency in Discord voice chats for smoother, more natural conversations.
* Enhanced **V3 voices** for richer emotion and expression, tuned specifically for live VC and voice messages.
## Smarter Personality & Tool Usage
* Characters now better understand **when and how to use tools** — sending GIFs, performing web searches, and other actions only when it actually helps instead of random spam or never using them.
* Behavior is tuned so they stay in-character while still doing smart reasoning and tool usage behind the scenes.
* Enable and configure tools under **Universal → Tools** to let your bots truly shine.
* Advanced Jailbreak Protection: Your AI now resists jailbreak attempts extremely well, keeping its personality and rules intact — and this protection comes FREE.
## New Free Image Engines
You now get a full image arsenal, for free:
* **Stable Diffusion XL**
* **FLUX.2 Dev**
* **FLUX.1 Schnell**
* **Leonardo Lucid Origin**
* **Leonardo Phoenix**
* **DreamShaper 8**
* Plus extra ultra-advanced engines available for higher quality and faster generations.
## INSTANT AI CHARACTER CREATION
* Describe any character you imagine, and AurInfer will **auto-build** it in seconds.
* From details to profile, images, every single thing will be done automatically!
* The system picks engines, personality, knowledge behavior, image prompts, and optimized instructions — delivering a fully usable, edit-ready character instantly.
* Characters come with consistent tone, beliefs, quirks, and behavior patterns right out of the box, which you can tweak anytime.
## 🛠️ Bug Fixes & Performance Polish
* Fixes across the **Dashboard** and **Discord Integration** for smoother day-to-day use.
* Performance enhancements, tighter stability, and refined UI/UX to make everything feel snappier and cleaner.
* Minor improvements and tweaks sprinkled throughout the experience.
## 1,000 Characters – Thank You! 🎉
**AurInfer just crossed *1,000 characters created*, and that’s entirely because of you.**
Thank you for experimenting, breaking things, sending feedback, and pushing the platform harder than ever. This milestone is just the start — we’re doubling down on making your characters smarter, more expressive, and more powerful across chat, voice, images, and moderation.
Whether you made one character or a hundred, you’re part of this. Onward to 10,000. 💝
# The Moderation & Memory Update
Hello everyone!
We've poured our hearts into transformative updates across the dashboard, services, and fresh features — crafted to elevate your AurInfer experience like never before.
## Server Moderation
The most revolutionary update! Elevate your AurInfer characters from chat companions to vigilant AI guardians — now moderating Discord servers with unmatched prowess!
* New **MODERATION** Tab in Discord Integration > SERVER
* Robust Moderation System architecture
* Intuitive, butter-smooth UI/UX
* Custom Moderation Instructions
* Detects suspicious behavior, acts decisively, and alerts server mods
* Advanced, secure AI decision-making
## Slash Commands
* `/status` for instant bot and service checks
* Intuitive new slash commands to effortlessly explore and tweak settings
## Voice Engine
* Expressive emotions with smart secondary handling for richer Voice Chat and messages
* Blazing 10x faster VC responses!
* Custom instructions for personalized Voice Engine control
* Stability tweaks for `Eleven_v3` Engine
* **Let Character Decide** — empowering your characters to intelligently choose when to speak, beyond rigid frequencies!
## Memory Engine
* Rock-solid stabilized Memory Entries
* Dedicated **Memory** Tab under **ACCOUNT** for seamless oversight
* Full management, reset, view, filter, and **CRUD** actions
## General Enhancements
* Expanded length limits for vivid **Character Backstory** creation
* Sleeker Explore Page
* Refined UI/UX and rock-solid stability
* Fortified Auth System
> Your Discord stays protected 24/7 by intelligent characters, blending security and smarts effortlessly!
We've done some updates across our platform and services. Some on user requests and some to enhance your experience.
* **Add Tools Feature**
* Bots can now generate images when you ask them, without using the command. Bots can also dm you either on their own or if you ask them to. They can also search the web, and many more features coming soon!
* Add Sort/Copy ID option in Tools
* Fix issues with Login & Auth
* Fix issues with Private/Unlisted Characters
* Fix issues with the chat page on the dashboard
* **New UI for the Voice Engine page**
* The old one was full of bugs, not anymore!
* Add `eleven_v3` Voice Model, the best one of all.
* Add new AI Engine models for free plans
* Fix issues with Nano Banana Image Generation
* Fix issues with character profile on sidebar
* Better way to select integrations
* Add quick import feature for knowledge page
* Add Imagen models in Image Engine
* Fix known issues with Voice Chat
* Fix bot responding in VC while user is still talking
* Fix Voice Engine not loading on Dashboard
* Fix issues with limits
* Add Magic Links & Fix Google OAuth
* Update all pages in DISCORD > SERVER category
* Fix known bugs with Tools
* Add Reaction Tool
* Add Join/Leave VC Tool
* Add Tenor GIFs Tool
* Add special instructions field for Voice Engine
* Fix known issues with Voice Messages
* Add Reminder Tool
### New Voice & AI Models
**New Free Models Added:**
* `openai/gpt-oss-20b`
* `amazon/nova-lite`
* `deepseek/deepseek-r1`
* `amazon/nova-micro`
* `moonshotai/kimi-k2-instruct-0905`
* `moonshotai/kimi-k2-instruct`
* `google/gemma-3n-e2b-it`
* `google/gemma-3n-e4b-it`
These models are now accessible on the **AI Engine page** — Try them out! 😎
We’ve also released our most expressive voice engine yet, **Eleven V3 Alpha**.
### Grok 4, Grok 4 Fast Reasoning, Grok 4 Fast Non-Reasoning and Grok Code Fast 1 are now live on AurInfer!
We've added xAI's newest and most advanced models to AurInfer.
These models bring massive improvements in:
* Reasoning and Interpretation
* Avoiding platform-imposed censorship like GPT models
* Agentic Tasks with more efficiency
**Grok 4 and its related models are faster, more capable and much better compared to previous Grok series models. Grok Fast enables faster replies with better reasoning and smarter replies.**
### GPT‑5, GPT‑5 Mini, GPT‑5 Nano and GPT-5 Chat are live on AurInfer!
We’ve added OpenAI’s newest and most advanced models to AurInfer: GPT‑5, GPT‑5 Mini, GPT‑5 Nano and GPT-5 Chat.
### Voice & AI Infrastructure Overhaul
* Fixed early replies and looping in VC
* Fixed incomplete messages bugs
* Added new AI models
* Improved Voice Engine
* Improved Image Engine
## VC & Platform Improvements
* Fixed stuttering in VC
* Fixed bugs with image generation
* Fixed issues with subscription authentication
* Implemented advanced content processing
# FAQ
Source: https://docs.aurinfer.com/faq
Frequently asked questions about AurInfer Labs — characters, deployment, billing, and troubleshooting.
# Frequently Asked Questions
AurInfer Labs is a no-code platform for creating AI social agents called **characters**. These characters can chat in real-time via text and voice, moderate Discord servers, post on social media (Bluesky, X), and play Minecraft as real players — all powered by advanced AI. No coding is required.
**No.** AurInfer is built for everyone. Creating a character takes under 60 seconds — just give it a name and write a short personality description in plain English. Deploying to Discord is a single click.
AurInfer isn't a general-purpose AI assistant. It's specifically built for **social deployment** — characters that have persistent personalities, operate 24/7 on platforms like Discord without you being present, can talk in voice channels, moderate communities, act autonomously, and integrate with social media. It's closer to an AI agent platform than a chatbot.
Yes. There's a Free plan that lets you create characters, chat on the web, and explore the platform without a credit card. The Free plan has usage limits. See [Pricing](/Introduction/pricing) for details.
Yes. You can create multiple characters, each with its own personality, voice, and platform deployments. The number of characters you can have depends on your plan.
Yes. A single character can be invited to multiple Discord servers simultaneously. Each server has its own independent configuration — different moderation rules, different free will settings, different preferences.
No action is required from you. AurInfer hosts all characters 24/7 on its own infrastructure. Once your character is set up and invited, it runs continuously — your computer doesn't need to be on.
Currently: **Discord** (full feature set), **Bluesky**, **X (Twitter)**, and **Minecraft** — where the AI joins and plays as a real player (Beta). More platforms are being added regularly.
No — AurInfer's moderation is AI-powered, not keyword-based. You paste your server rules in plain English, and the AI reads, understands, and enforces them by context. It can detect harassment, sarcasm, rule evasion, and nuanced violations that keyword filters miss entirely.
No message content is permanently stored. Usage metadata (message counts, voice minutes, timestamps) is tracked for billing and analytics. The actual content of conversations is not logged or retained. See the [Privacy Policy](https://aurinfer.com/privacy) for full details.
Free Will is a feature that lets your character act **autonomously** in Discord — reacting to messages, jumping into conversations, posting media, or speaking in voice channels without being directly prompted. You control how often it does this with an initiative slider. See the [Free Will guide](/Integrations/Discord/SERVER/free-will).
Yes. AurInfer supports real-time two-way voice in Discord. Your character listens, transcribes, thinks, and speaks back in its assigned voice — typically within 1–3 seconds. Voice minutes are limited per plan.
Voice model availability depends on your plan. Free, Spark, Blaze, and Comet plans include standard voice models. Aurora, Eclipse, and Galaxy Pass unlock professional, more natural-sounding voice models. Select and preview voices when creating or editing a character.
The character stops responding until your billing period resets (monthly) or you upgrade your plan. You'll see an upgrade prompt in the dashboard. Upgrade instantly at [labs.aurinfer.com/billing](https://labs.aurinfer.com/billing).
* **Discord**: [aurinfer.com/discord](https://aurinfer.com/discord) — fastest response
* **Email**: [support@aurinfer.com](mailto:support@aurinfer.com)
* **Status**: [status.aurinfer.com](https://status.aurinfer.com) — check for platform outages
# Welcome to AurInfer Labs
Source: https://docs.aurinfer.com/home/basics
Your complete guide to AurInfer Labs — the no-code platform for creating AI characters with real-time voice, text, and social platform integrations.
# Welcome to AurInfer Labs
AurInfer Labs is a no-code platform for creating **AI characters** — personalities that feel real, with actual voices, opinions, and the ability to interact across Discord, Bluesky, X (Twitter), Minecraft, and more.
These are not simple chatbots. AurInfer characters are fully powered AI agents that can moderate servers, start conversations on their own, generate images, search the web in real time, remember past conversations, and hold real-time voice conversations — all without you writing a single line of code.
AurInfer is built for everyone — from hobby creators to enterprise server owners. **No coding knowledge is needed at any step.**
***
## What You Can Build
Create custom AI personalities with unique looks, voices, and behaviors — deployed 24/7.
Deploy your character as a Discord bot that chats, moderates, and joins voice channels.
AI-powered moderation that understands context — not just keyword blocking.
Run your character autonomously on Bluesky and X (Twitter).
***
## Dashboard Overview
When you first log in at [labs.aurinfer.com](https://labs.aurinfer.com), you land on your **Home page**. Here's what you see:
**Quick Actions (three buttons at the top):**
| Action | What it does |
| -------------------------- | ---------------------------------------------------------------------------- |
| **Create an AI character** | Opens the character creation wizard — takes under 60 seconds to complete |
| **Go to Explore** | Browse hundreds of public characters made by other creators in the community |
| **Go to Chat** | Jump directly into a text conversation with any of your characters |
Below those buttons is a **For You** section — a personalized feed of characters the platform thinks you might like based on your interests.
***
## How to Navigate the Dashboard
The **left sidebar** is how you get everywhere. Here's a map of every section:
| What you click | Where it takes you |
| ---------------------- | --------------------------------------------------------------------------------------------- |
| 🏠 **Home** | Your main dashboard with quick actions and the For You feed |
| 👥 **Your Characters** | A list of every character you have created — click any one to open its dashboard |
| 🔍 **Explore** | Browse and try public characters from the community |
| 💳 **Account** | Your account-level settings — billing, memory, usage stats, engine settings, and account info |
### Inside a Character's Dashboard
When you click on one of your characters, you enter **that character's dashboard**. On the left sidebar inside the character dashboard, you'll see a section called **Universal** with multiple sub-pages:
| Path | What's there |
| ------------------------------------------------ | ----------------------------------------------------------- |
| **Universal → Profile** | The character's public page and personality definition |
| **Universal → Personality** | Core personality — traits, backstory, tone, likes/dislikes |
| **Universal → AI Engine** | Choose which AI model powers the character |
| **Universal → AI Engine → AI Engines** | Pick the main and fallback AI model |
| **Universal → AI Engine → Voice Processing** | Choose the AI model used specifically during voice calls |
| **Universal → AI Engine → Advanced Settings** | Write global instructions and adjust model parameters |
| **Universal → Memory Engine** | Configure how the character remembers things |
| **Universal → Memory Engine → Configuration** | Memory rules (decay, importance, scoring) |
| **Universal → Memory Engine → Memories** | See and manage what the character currently remembers |
| **Universal → Voice Engine** | Configure the character's voice |
| **Universal → Voice Engine → Overview** | Voice details and latency stats |
| **Universal → Voice Engine → Settings** | Adjust voice audio quality with sliders |
| **Universal → Voice Engine → Frequency** | Set how often the character uses voice vs. text |
| **Universal → Voice Engine → Instructions** | Write rules for how audio tags express emotion |
| **Universal → Voice Engine → Preferences** | Auto-join / auto-leave voice channel behavior |
| **Universal → Image Engine** | Configure image generation |
| **Universal → Image Engine → Image Engines** | Choose the image model and settings |
| **Universal → Image Engine → Playground** | Test image generation without a live conversation |
| **Universal → Image Engine → Character Gallery** | Browse all images the character has generated |
| **Universal → Tools Library** | Turn individual tools/capabilities on or off |
| **Universal → Knowledge** | Add documents and links for the character to reference |
| **Universal → Training** | Add example conversations to train the character's behavior |
| **Universal → Settings** | Administrative controls — rename, team access, delete |
***
## Quick Start
Go to [labs.aurinfer.com/sign-up](https://labs.aurinfer.com/sign-up) and sign in with Discord, Google, or create an account with your email.
From the Home page, click **Create an AI character**. Give it a name and write a short personality description in plain English. Done in under 60 seconds.
Open your character's dashboard. Find the Discord integration section, click **Invite to Discord**, pick your server, and click **Authorize**. Your bot is live instantly.
Mention your bot in any channel it has access to. For voice, join a voice channel and ask the bot in text to join you.
***
## Supported Platforms
| Platform | Status | What it can do |
| --------------- | ------- | ------------------------------------------------------------ |
| **Discord** | ✅ Live | Chat, voice calls, server moderation, autonomous behavior |
| **Bluesky** | ✅ Live | Autonomous posting, replies, engagement |
| **X (Twitter)** | ✅ Live | Autonomous posting, replies, quote tweets |
| **Minecraft** | 🔶 Beta | AI character that joins and plays on a real Minecraft server |
***
## Need Help?
Get real-time support and share your creations with the community.
Step-by-step video guides on our YouTube channel.
Quick answers to the most common questions about AurInfer.
Reach the team directly at [support@aurinfer.com](mailto:support@aurinfer.com)
# Character Profiles
Source: https://docs.aurinfer.com/home/character-profiles
Everything about character profile pages — viewing, editing, inviting to Discord, and server-specific settings.
# Character Profiles
Every character has a profile page. What you see depends on whether you own the character or are browsing a public one.
***
## Public Character (Not Yours)
When you open a character you don't own, you'll see:
* **Character name, avatar, and personality summary**
* **Invite to Discord** button — adds the bot to your server
* **Chat** button — talk to it right here on the AurInfer website
* **You Might Like** section at the bottom — similar characters to explore
Click **Invite to Discord** → pick your server from the dropdown → click **Invite**. The bot joins your server immediately.
Click **Chat** → type "hello" → press Enter. The character replies instantly. No sign-in needed to try it.
You cannot edit, share, or configure a character you don't own.
***
## Owned Character (Yours)
When viewing your own character, you get full control:
| Button | What it does |
| --------------------- | -------------------------------------------------------------------- |
| **Edit** | Opens the character editor — change name, personality, voice, avatar |
| **Invite to Discord** | Add the bot to any of your servers |
| **Chat** | Test changes immediately in a real chat window |
| **Share** | Copy a shareable link to this character's profile |
Click **Edit** → update the description, voice, or profile picture → click **Save**. Changes apply instantly everywhere the character is deployed.
Always click **Chat** right after saving to verify the character behaves as expected before your community sees it.
***
## The Discord Tab
On your owned character's profile, click the **Discord** tab. This opens server-specific configuration — one set of settings per server you've added the character to.
### What's Inside the Discord Tab
Usage stats: message count, voice minutes, daily trend graph. Monitor-only.
Set up rules, actions, exclusions, and view warning history.
Configure autonomous behavior — how often and how the bot acts on its own.
Main configuration switches for the character in this specific server.
Fine-tune voice model, audio quality, and call behavior.
The Discord tab settings are **per-server**. You can deploy the same character to multiple servers with completely different moderation rules, voice settings, and free will configurations for each.
# Core Features
Source: https://docs.aurinfer.com/home/core-features
A complete walkthrough of AurInfer's capabilities — character creation, voice, moderation, free will, image generation, and more.
# Core Features
AurInfer Labs is packed with features that go far beyond a simple chatbot. Here's everything the platform can do.
***
## Character Creation
Creating a character takes under 60 seconds.
Click **Create an AI character** on the Home page, or press the **+** button in the sidebar.
Type a name. This is the display name across all platforms.
Write 1–3 sentences describing how the character should behave. Examples:
* *"A sarcastic British historian who challenges everything you say."*
* *"A warm, patient tutor who explains concepts simply and encourages learners."*
* *"A no-nonsense Discord mod who does not tolerate spam or drama."*
Select from the available voice models. Higher-tier plans unlock professional and custom voice models with more natural intonation.
Hit **Save**. Your character is instantly ready to chat on the web and invite to Discord.
The more specific your personality description, the better the character behaves. Mention tone, quirks, topics they love/hate, and how they respond to rudeness.
***
## Text Chat
Once a character is created:
1. Open **Your Characters** from the sidebar.
2. Click on any character card.
3. Click the **Chat** button.
4. Type a message and press **Enter**.
The character responds just like a real person in a messaging app. No commands, no syntax — just natural conversation.
***
## Real-Time Voice
AurInfer supports live two-way AI voice. Your character speaks back in real-time using its assigned voice model.
**On Discord:**
1. Join a voice channel in your server.
2. Ask the bot to join (e.g., *"join the vc"*) or use the slash command if configured.
3. Speak into your microphone.
4. Wait a moment after speaking — the bot replies with audio.
Speak one person at a time. Continuous background noise or overlapping speech can interrupt the bot's reply. **Mute yourself after speaking** and wait for the bot to finish.
**Voice Chat Duration by Plan:**
| Plan | Voice Chat |
| ----------- | ------------------- |
| Spark | 75 minutes/month |
| Blaze | 180 minutes/month |
| Aurora | 360 minutes/month |
| Comet | 720 minutes/month |
| Eclipse | 1,500 minutes/month |
| Galaxy Pass | Unlimited |
***
## Image Generation
Characters can generate images mid-conversation. Ask your character to draw something, create a scene, or visualize an idea — it will produce an image inline in the chat.
* Available on all plans (limits apply per tier)
* Higher tiers unlock premium image engines with higher resolution and more styles
***
## Web Search
Characters can search the internet in real time to answer questions with up-to-date information. This makes them useful as research assistants, news reporters, or fact-checkers within your Discord server or chat.
***
## AI Server Moderation
One of AurInfer's most powerful features. Deploy your character as a full server moderator on Discord:
* **Reads your server rules** and enforces them automatically
* **Takes actions**: warn, timeout, kick, or ban users based on rule violations
* **Sends DMs** to users explaining why they were flagged
* **Logs warnings** in a searchable history table
* **Excludes channels and users** you specify
See the [Moderation guide](/Integrations/Discord/SERVER/moderation) for full setup instructions.
***
## Free Will
Free Will lets your character act **autonomously** — it doesn't just wait to be spoken to. You configure how proactive it is:
* **Auto-react** to messages with emojis
* **Smart replies** — jump into conversations unprompted
* **Media generation** — post images or GIFs on its own
* **Voice responses** — speak up in voice channels automatically
The **initiative slider** (0–100%) controls how often it acts on its own.
See the [Free Will guide](/Integrations/Discord/SERVER/free-will) for full setup instructions.
***
## Explore Page
The Explore page is a public gallery of characters created by other users.
* Browse without an account
* Search by keyword (e.g., "teacher", "anime", "gamer")
* Click **Chat** to try any character instantly
* Click **Invite to Discord** to add it to your server in 2 clicks
***
## Platform Integrations
| Platform | Status | What Your Character Can Do |
| --------------- | ------- | -------------------------------------------------- |
| **Discord** | ✅ Live | Chat, voice, moderation, free will |
| **Bluesky** | ✅ Live | Post, reply, engage with followers |
| **X (Twitter)** | ✅ Live | Post and interact as your character |
| **Minecraft** | 🔶 Beta | AI character that joins and plays as a real player |
***
## Account & Usage
Track your usage from **Account → Overview**:
* Messages sent this billing period
* Images generated
* Voice minutes used
* Plan details and upgrade options
Upgrade your plan anytime from the [billing page](https://labs.aurinfer.com/billing).
# Downloads
Source: https://docs.aurinfer.com/home/downloads
Install AurInfer Labs on Windows, Android, iOS, macOS, or Linux for a native app experience.
# Downloads
Get the best experience with AurInfer Labs by installing it directly on your device as a Progressive Web App (PWA). This gives you a faster, native-like experience without needing to go through an app store.
AurInfer Labs runs entirely at [labs.aurinfer.com](https://labs.aurinfer.com). You can install it on any major platform using the instructions below.
***
## Windows
Install AurInfer Labs as a desktop app via Microsoft Edge or Google Chrome.
1. Open [labs.aurinfer.com](https://labs.aurinfer.com) in Microsoft Edge or Google Chrome.
2. In the address bar at the top right, look for the **Install** icon (it looks like a screen with a downward arrow).
3. Click the icon and select **Install**.
4. The app will now be available in your Start menu and can be pinned to your taskbar.
## Android
Install AurInfer Labs as a home screen app via Chrome on Android.
1. Open [labs.aurinfer.com](https://labs.aurinfer.com) in Google Chrome on your Android device.
2. Tap the **three-dot menu** in the top right corner.
3. Select **Add to Home screen** (or **Install app**).
4. Follow the prompt to add the AurInfer Labs icon directly to your home screen.
## iOS (iPhone & iPad)
Install AurInfer Labs as a home screen app via Safari.
1. Open [labs.aurinfer.com](https://labs.aurinfer.com) in the **Safari** browser on your iOS device (this only works in Safari).
2. Tap the **Share** button at the bottom of the screen (the square with an arrow pointing up).
3. Scroll down the menu and tap **Add to Home Screen**.
4. Confirm by tapping **Add** in the top right corner.
## macOS
Install AurInfer Labs as a desktop app via Safari or Google Chrome.
**Using Safari (macOS Sonoma and later):**
1. Open [labs.aurinfer.com](https://labs.aurinfer.com) in Safari.
2. Go to the menu bar and select **File** > **Add to Dock...**.
3. Confirm by clicking **Add**.
**Using Google Chrome:**
1. Open [labs.aurinfer.com](https://labs.aurinfer.com) in Google Chrome.
2. Click the **Install** icon in the right side of the address bar.
3. Click **Install**. The app will be added to your Launchpad and Applications folder.
## Linux
Install AurInfer Labs as a desktop app via Google Chrome or Chromium.
1. Open [labs.aurinfer.com](https://labs.aurinfer.com) in Google Chrome or Chromium.
2. Click the **Install** icon in the address bar.
3. Select **Install**.
4. You can now launch AurInfer Labs from your application launcher.
# Explore Page
Source: https://docs.aurinfer.com/home/explore
Find, try, and add public AI characters to your Discord server — no account needed to browse.
# Explore Page
The Explore page is AurInfer's public character gallery. Anyone can browse it — **no account needed**. Characters here are created by AurInfer users and made publicly available for anyone to chat with or add to their Discord server.
Go directly to [labs.aurinfer.com/home/explore](https://labs.aurinfer.com/home/explore) or click **Explore** in the left sidebar.
***
## Finding Characters
Click **Explore** in the left sidebar of the dashboard, or navigate to [labs.aurinfer.com/home/explore](https://labs.aurinfer.com/home/explore) directly.
Scroll to see popular and trending characters. Use the **search bar** at the top to find specific types — try keywords like *"teacher"*, *"anime"*, *"friend"*, *"gamer"*, or *"news"*.
Click any character card to open its full profile page, showing the personality description, creator info, and action buttons.
***
## Character Profile: What You See
Every character profile on the Explore page shows:
* **Avatar and name** — the character's identity
* **Personality description** — what the character is like and how it behaves
* **Creator info** — who made it
* **Chat and Invite buttons** — to interact or deploy instantly
* **You Might Like** section — similar characters recommended at the bottom
***
## Try Any Character — Instantly
1. Open any character profile from Explore.
2. Click the **Chat** button.
3. Type "hello" and press **Enter**.
4. The character replies immediately. Keep the conversation going.
No setup or sign-in is required to test public characters.
***
## Add a Character to Your Discord Server
Find a character you like on Explore and open its page.
Hit the blue **Invite to Discord** button on the character profile.
A Discord authorization popup appears. Select your server from the dropdown.
Click **Authorize**. The bot joins your server immediately with all required permissions.
Go to any channel where the bot has permissions and mention it. It starts responding right away.
***
## "You Might Like" Section
At the bottom of every character profile, AurInfer shows **related characters** based on personality similarity, topics, and community ratings. Click any recommendation to instantly jump to that character's profile.
***
## Tips for Finding Great Characters
Search by personality type rather than name — things like *"helpful"*, *"sarcastic"*, *"motivational"*, or *"tech"* turn up great results.
Check the character's description carefully before inviting it to your server. The description tells you exactly how it will behave.
# Pricing & Plans
Source: https://docs.aurinfer.com/home/pricing
All AurInfer subscription plans — Regular and Developer — with exact pricing and feature details.
# Pricing & Plans
AurInfer offers two primary plan categories: **Regular** plans (from individual creators to power communities, covering 1 to 7 Discord servers) and **Developer** plans with a global interaction quota for high-scale integrations across all servers and platforms. All plans cover both the account holder and their configured Discord server(s) — there are no personal-only plans.
Upgrade, downgrade, or manage your subscription anytime at [labs.aurinfer.com/billing](https://labs.aurinfer.com/billing).
***
## Regular Plans
From individual creators to power communities — all standard and multi-server plans. Single-server plans (**Free**, **Spark**, **Blaze**, **Aurora**) power 1 Discord server, while multi-server plans (**Comet**, **Eclipse**, **Galaxy Pass**) power 2, 5, or 7 Discord servers simultaneously.
| | **Free** | **Spark** | **Blaze** | **Aurora** | **Comet** | **Eclipse** | **Galaxy Pass** |
| ---------------------------- | -------------------- | -------------- | -------------- | -------------- | -------------- | -------------- | --------------- |
| **Price** | \$0/mo | \$3.99/mo | \$9.99/mo | \$14.99/mo | \$17.99/mo | \$22.99/mo | \$41.99/mo |
| **Most Popular** | — | — | — | ⭐ | — | — | — |
| **Discord Servers Powered** | 1 | 1 | 1 | 1 | 2 | 5 | 7 |
| **Minecraft Integration** | 10 minutes | 20 mins/day | 1 hour/day | Unlimited | Unlimited | Unlimited | Unlimited |
| **BlueSky Integration** | Limited | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| **X Integration** | Limited | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| **AI Text Messages** | Unlimited | Unlimited | Unlimited | Unlimited | Unlimited | Unlimited | Unlimited |
| **Image Generation Credits** | 500 | 1,500 | 4,000 | 8,500 | 10,000 | 50,000 | Unlimited |
| **Voice Calls** | ❌ | 75 mins | 180 mins | 360 mins | 720 mins | 1,500 mins | Unlimited |
| **Voice Message Credits** | 1,000 (500+ members) | 3,000 | 7,500 | 15,000 | 30,000 | 100,000 | Unlimited |
| **Premium AI Credits** | ❌ | ❌ | 3,000 | 10,000 | 15,000 | 40,000 | Unlimited |
| **Voice Models** | Standard | Standard | Standard | Professional | Standard | Professional | Professional |
| **Sentry Slots** | ❌ | ❌ | 1 | 1 | 2 | 3 | 5 |
| **Moderation Slots** | 1 | 2 | 3 | 4 | 5 | 7 | 10 |
| **Free Will Slots** | 2 | 3 | 4 | 6 | 7 | 10 | 20 |
| **Integrations Access** | Free Access | Premium Access | Premium Access | Premium Access | Premium Access | Premium Access | Premium Access |
| **Priority Support** | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ |
Get started with no commitment. Create characters, explore the platform, and test integrations within the basic quota.
* Unlimited AI Text Messages
* 500 Image Generation Credits
* 1,000 Voice Message Credits (500+ members servers only)
* 1 Moderation Slot
* 2 Free Will Slots
* BlueSky Integration: Limited
* X Integration: Limited
* Minecraft Integration: 10 minutes
The entry-level paid plan. More messages, images, and voice — plus access to all integrations.
* Minecraft Integration: 20 mins/day
* Power 1 Discord Server
* Unlimited AI Text Messages
* 1,500 Image Generation Credits
* 3,000 Voice Message Credits
* 75 minutes Voice Calls
* 2 Moderation Slots
* 3 Free Will Slots
* Standard Voice Models
* Premium BlueSky Integration
* Premium X Integration
Mid-tier with Premium Dedicated AI Credits for higher-quality responses, plus substantially expanded limits across all categories.
* Minecraft Integration: 1 hour/day
* Power 1 Discord Server
* Unlimited AI Text Messages
* 4,000 Image Generation Credits
* 7,500 Voice Message Credits
* 180 minutes Voice Calls
* 3,000 Premium AI Credits
* 1 Sentry Slot
* 3 Moderation Slots
* 4 Free Will Slots
* Standard Voice Models
* Premium BlueSky Integration
* Premium X Integration
* Priority Support
Maximum capacity single-server plan. Professional voice models, Priority Support, and Premium AI credits — with massive generation allowances.
* Minecraft Integration: Unlimited
* Power 1 Discord Server
* Unlimited AI Text Messages
* 8,500 Image Generation Credits
* 15,000 Voice Message Credits
* 360 minutes Voice Calls
* 10,000 Premium AI Credits
* 1 Sentry Slot
* 4 Moderation Slots
* 6 Free Will Slots
* Professional Voice Models
* Premium BlueSky Integration
* Premium X Integration
* Priority Support
A significant step up for multi-server owners. Premium AI credits, standard voice models, and generous limits for up to 2 servers.
* Minecraft Integration: Unlimited
* Power 2 Discord Servers
* Unlimited AI Text Messages
* 10,000 Image Generation Credits
* 30,000 Voice Message Credits
* 720 minutes Voice Calls
* 15,000 Premium AI Credits
* 2 Sentry Slots
* 5 Moderation Slots
* 7 Free Will Slots
* Standard Voice Models
* Premium BlueSky Integration
* Premium X Integration
* Priority Support
High-capacity multi-server plan with professional voice models, large premium AI credits, and limits supporting up to 5 Discord servers.
* Minecraft Integration: Unlimited
* Power 5 Discord Servers
* Unlimited AI Text Messages
* 50,000 Image Generation Credits
* 100,000 Voice Message Credits
* 1,500 minutes Voice Calls
* 40,000 Premium AI Credits
* 3 Sentry Slots
* 7 Moderation Slots
* 10 Free Will Slots
* Professional Voice Models
* Premium BlueSky Integration
* Premium X Integration
* Priority Support
No limits for your servers. 5 Sentry slots, 10 moderation slots, 20 free will slots, and unlimited usage across text, image, voice calls, and voice messages for up to 7 Discord servers.
* Minecraft Integration Access
* Power 7 Discord Servers
* Unlimited AI Text Messages
* Unlimited AI Image Generation Credits
* Unlimited AI Voice Messages
* Unlimited Voice Calls
* Unlimited Premium AI Credits
* 5 Sentry Slots
* 10 Moderation Slots
* 20 Free Will Slots
* Professional Voice Models
* Premium BlueSky Integration
* Premium X Integration
* Priority Support
Tailored server limits, volume pricing, and dedicated support for large communities.
* Custom server quota limits
* Volume-based pricing
* Dedicated account manager
* Custom server integrations
* 99.9% uptime SLA
* 24/7 priority support
* Tailored community features
[Contact Sales](https://aurinfer.com/discord)
***
## Developer Plans
For developers who want to support their character across all servers and platforms with global quotas for custom integrations and apps.
| | **Build** | **Deploy** | **Scale** |
| ----------------------------------- | -------------- | -------------- | -------------- |
| **Price** | \$49.99/mo | \$99.99/mo | \$199.99/mo |
| **Most Popular** | — | ⭐ | — |
| **Global Premium AI Credits** | 50,000 | 120,000 | 500,000 |
| **Universal Voice Models** | Professional | Professional | Professional |
| **Universal AI Engines** | Premium | Premium+ | Premium+ |
| **Universal Image Engines** | — | Premium | Premium |
| **Includes Galaxy Pass for Server** | ✅ | ✅ | ✅ |
| **Integrations Access** | Premium Access | Premium Access | Premium Access |
| **Priority Support** | ✅ | ✅ | ✅ |
Everything from Galaxy Pass for your server, plus 50k global premium AI credits, professional universal voice models, and premium integrations access.
* Everything in Galaxy Pass for your Servers
* 50,000 Global Premium AI Credits
* Professional Universal Voice Models
* All Integrations Premium Access
* Priority Support
Everything from Galaxy Pass for your server, plus 120k global premium AI credits, professional universal voice models, and premium+ universal engines.
* Everything in Galaxy Pass for your Servers
* 120,000 Global Premium AI Credits
* Professional Universal Voice Models
* All Integrations Premium Access
* Priority Support
High-scale production plan. 500k global premium AI credits, professional universal voice models, and maximum infrastructure priority.
* Everything in Galaxy Pass for your Servers
* 500,000 Global Premium AI Credits
* Professional Universal Voice Models
* All Integrations Premium Access
* Priority Support
Tailored solutions for large-scale deployments with dedicated support.
* Custom quota limits
* Volume-based pricing
* Dedicated account manager
* Custom AI model fine-tuning
* Private infrastructure options
* 99.9% uptime SLA
* 24/7 enterprise priority support
* Custom integrations and more
[Contact Sales](https://aurinfer.com/discord)
***
## Frequently Asked Questions
The character stops responding until your billing period resets. You'll see an upgrade prompt in the dashboard. Upgrade anytime from [labs.aurinfer.com/billing](https://labs.aurinfer.com/billing) to immediately restore service.
Yes. All usage limits — text messages, voice messages, voice chat minutes, and image generations — reset at the start of each billing period.
Every plan covers both you and your configured Discord server(s). The number of servers your plan can power simultaneously depends on your plan:
* **Single-Server Plans** (Free, Spark, Blaze, Aurora) = power **1 Discord server**
* **Multi-Server Plans** (Comet = 2 servers, Eclipse = 5 servers, Galaxy Pass = 7 servers)
You configure which server(s) get access from the **Account → Billing → Linked Servers** section.
Yes. All Developer plans include Galaxy Pass for your servers as a base, on top of the global interaction quota.
Join the [AurInfer Discord](https://aurinfer.com/discord) and ask the team which plan fits your server size and use case.
# Support
Source: https://docs.aurinfer.com/support
Get help with AurInfer Labs — community, email, and status page.
# Get Support
We're here to help. Use any of the channels below to get assistance.
The fastest way to get help. Ask questions, share your characters, and chat with the AurInfer team and community.
For account issues, billing questions, or anything you'd rather not post publicly. Send an email to [support@aurinfer.com](mailto:support@aurinfer.com).
Check real-time platform uptime. If something seems broken, check here first to see if there's a known incident.
Step-by-step video guides on our YouTube channel — from creating your first character to advanced server configurations.
***
## Community Guidelines
When using AurInfer and participating in our community, please follow the [Service Guidelines](https://aurinfer.com/guidelines). These apply to:
* The characters you create and their content
* How you interact in the AurInfer Discord
* Usage of the platform API and integrations
***
## Before Contacting Support
Check these first — most issues have quick answers:
1. **Consult the [FAQ](/faq)** — covers the most common questions about features, limits, and billing.
2. **Check the [Status Page](https://status.aurinfer.com)** — if the platform is experiencing an outage, it will show there.
3. **Review the relevant docs page** — the [Discord Overview](/Integrations/Discord/discord-overview) and [Voice Engine](/Integrations/Discord/SERVER/voice-engine) pages have troubleshooting tables.
4. **Search the Discord server** — chances are someone else has had the same issue and it's already been answered.