airunner

✉️ Get notified when the packaged version releases

🌍 Language Support

🫰 Request language support

💾 Installation Quick Start

⚙️ System Requirements

🔧 Installation Steps

1. Install system requirements

   sudo apt update && sudo apt upgrade -y
   sudo apt install -y make build-essential libssl-dev zlib1g-dev libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev xz-utils tk-dev libffi-dev liblzma-dev python3-openssl git nvidia-cuda-toolkit pipewire libportaudio2 libxcb-cursor0 gnupg gpg-agent pinentry-curses espeak xclip cmake qt6-qpa-plugins qt6-wayland qt6-gtk-platformtheme mecab libmecab-dev mecab-ipadic-utf8 libxslt-dev mkcert
   sudo apt install espeak
   sudo apt install espeak-ng-espeak
   

2. Create airunner directory

   sudo mkdir ~/.local/share/airunner
   sudo chown $USER:$USER ~/.local/share/airunner
   

3. Install AI Runner - Python 3.13+ required pyenv and venv are recommended (see wiki for more info)

   pip install "typing-extensions==4.13.2"
   pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
   pip install airunner[all_dev]
   

4. Run AI Runner

   airunner
   

For more options, including Docker, see the Installation Wiki.

Basic Usage

• Run AI Runner: airunner
• Run the downloader: airunner-setup
• Build templates: airunner-build-ui

🤖 Models

~/.local/share/airunner
├── art
│   └── models
│       ├── SD 1.5
│       │   ├── controlnet
│       │   ├── embeddings
│       │   ├── inpaint
│       │   ├── lora
│       │   └── txt2img
│       ├── Flux (not supported yet)
│       ├── SDXL 1.0
│       │   ├── controlnet
│       │   ├── embeddings
│       │   ├── inpaint
│       │   ├── lora
│       │   └── txt2img
│       └── SDXL Turbo
│           ├── controlnet
│           ├── embeddings
│           ├── inpaint
│           ├── lora
│           └── txt2img

Chatbot Mood and Conversation Summary System

• The chatbot’s mood and conversation summary system is always enabled by default. The bot’s mood and emoji are shown with each bot message.
• When the LLM is updating the bot’s mood or summarizing the conversation, a loading spinner and status message are shown in the chat prompt widget. The indicator disappears as soon as a new message arrives.
• This system is automatic and requires no user configuration.
• For more details, see the LLM Chat Prompt Widget README.
• The mood and summary engines are now fully integrated into the agent runtime. When the agent updates mood or summarizes the conversation, it emits a signal to the UI with a customizable loading message. The chat prompt widget displays this message as a loading indicator.
• See src/airunner/handlers/llm/agent/agents/base.py for integration details and src/airunner/api/chatbot_services.py for the API function.

🔍 Aggregated Search Tool

AI Runner includes an Aggregated Search Tool for querying multiple online services from a unified interface. This tool is available as a NodeGraphQt node, an LLM agent tool, and as a Python API.

Supported Search Services:

• DuckDuckGo (no API key required)
• Wikipedia (no API key required)
• arXiv (no API key required)
• Google Custom Search (requires GOOGLE_API_KEY and GOOGLE_CSE_ID)
• Bing Web Search (requires BING_SUBSCRIPTION_KEY)
• NewsAPI (requires NEWSAPI_KEY)
• StackExchange (optional STACKEXCHANGE_KEY for higher quota)
• GitHub Repositories (optional GITHUB_TOKEN for higher rate limits)
• OpenLibrary (no API key required)

API Key Setup:

• Set the required API keys as environment variables before running AI Runner. Only services with valid keys will be queried.
• Example:

  export GOOGLE_API_KEY=your_google_api_key
  export GOOGLE_CSE_ID=your_google_cse_id
  export BING_SUBSCRIPTION_KEY=your_bing_key
  export NEWSAPI_KEY=your_newsapi_key
  export STACKEXCHANGE_KEY=your_stackexchange_key
  export GITHUB_TOKEN=your_github_token
  

Usage:

• Use the Aggregated Search node in NodeGraphQt for visual workflows.
• Call the tool from LLM agents or Python code:

  from airunner.components.tools import AggregatedSearchTool
  results = await AggregatedSearchTool.aggregated_search("python", category="web")
  

• See src/airunner/tools/README.md for more details.

Note:

• DuckDuckGo, Wikipedia, arXiv, and OpenLibrary do not require API keys and can be used out-of-the-box.
• For best results and full service coverage, configure all relevant API keys.

🔒 Enabling HTTPS for the Local HTTP Server

AI Runner’s local server enforces HTTPS-only operation for all local resources. HTTP is never used or allowed for local static assets or API endpoints. At startup, the server logs explicit details about HTTPS mode and the certificate/key in use. Security headers are set and only GET/HEAD methods are allowed for further hardening.

How to Enable SSL/TLS (HTTPS)

1. Automatic Certificate Generation (Recommended):

   • By default, AI Runner will auto-generate a self-signed certificate in ~/.local/share/airunner/certs/ if one does not exist. No manual steps are required for most users.
   • If you want to provide your own certificate, place cert.pem and key.pem in the certs directory under your AI Runner base path.

2. Manual Certificate Generation (Optional):

   • You can manually generate a self-signed certificate with:

     airunner-generate-cert
     

   • This will create cert.pem and key.pem in your current directory. Move them to your AI Runner certs directory if you want to use them.

3. Configure AI Runner to Use SSL:

   • The app will automatically use the certificates in the certs directory. If you want to override, set the environment variables:

     export AIRUNNER_SSL_CERT=~/path/to/cert.pem
     export AIRUNNER_SSL_KEY=~/path/to/key.pem
     airunner
     

   • The server will use HTTPS if both files are provided.

4. Access the App via https://localhost:<port>

   • The default port is 5005 (configurable in src/airunner/settings.py).
   • Your browser may warn about the self-signed certificate; you can safely bypass this for local development.

Security Notes

• For production or remote access, use a certificate from a trusted CA.
• Never share your private key (key.pem).
• The server only binds to 127.0.0.1 by default for safety.
• For additional hardening, see the Security guide and the code comments in local_http_server.py.

🔑 Generate a Self-Signed Certificate (airunner-generate-cert)

You can generate a self-signed SSL certificate for local HTTPS with a single command:

airunner-generate-cert

This will create cert.pem and key.pem in your current directory. Use these files with the local HTTP server as described above.

See the SSL/TLS section for full details.

Additional Requirements for Trusted Local HTTPS

• For a browser-trusted local HTTPS experience (no warnings), install mkcert:

  # On Ubuntu/Debian:
  sudo apt install libnss3-tools
  brew install mkcert   # (on macOS, or use your package manager)
  mkcert -install
  

• If mkcert is not installed, AI Runner will fall back to OpenSSL self-signed certificates, which will show browser warnings.
• See the SSL/TLS section for details.

🛠️ Command Line Tools

AI Runner provides several CLI commands for development, testing, and maintenance. Below is a summary of all available commands:

Usage Examples:

# Launch the app
airunner

# Download models and set up data
airunner-setup

# Build UI Python files from .ui templates
airunner-build-ui

# Compile translation files
airunner-compile-translations

# Run all tests
airunner-tests

# Generate a test coverage report
airunner-test-coverage-report

# Run Docker build or management tasks
airunner-docker

# Generate a new Alembic migration
airunner-generate-migration

# Generate a self-signed SSL certificate
airunner-generate-cert

# Run mypy type checking on a file
airunner-mypy src/airunner/components/document_editor/gui/widgets/document_editor_widget.py

For more details on each command, see the Wiki or run the command with --help if supported.

🚀 Slash Tools (Chat Slash Commands)

AI Runner supports a set of powerful chat slash commands, known as Slash Tools, that let you quickly trigger special actions, tools, or workflows directly from the chat prompt. These commands start with a / and can be used in any chat conversation.

How to Use

• Type / in the chat prompt to see available commands (autocomplete is supported in the UI).
• Each slash command maps to a specific tool, agent action, or workflow.
• The set of available commands is extensible and may include custom or extension-provided tools.

Current Slash Commands

Note:

• Some slash tools (like /b for browser and /a for image) return an immediate confirmation message (e.g., “Ok, I’ve navigated to …”, “Ok, generating your image…”).
• Others (like /s for search or /w for workflow) do not return a direct message, but instead show a loading indicator until the result is ready.
• The set of available slash commands is defined in SLASH_COMMANDS in src/airunner/settings.py and may be extended in the future.

For a full list of supported slash commands, type /help in the chat prompt or see the copilot-instructions.md.

Contributing

We welcome pull requests for new features, bug fixes, or documentation improvements. You can also build and share extensions to expand AI Runner’s functionality. For details, see the Extensions Wiki.

Take a look at the Contributing document and the Development wiki page for detailed instructions.

🧪 Testing & Test Organization

AI Runner uses pytest for all automated testing. Test coverage is a priority, especially for utility modules.

Test Directory Structure

• Headless-safe tests:
  • Located in src/airunner/utils/tests/
  • Can be run in any environment (including CI, headless servers, and developer machines)
  • Run with:

    pytest src/airunner/utils/tests/
    

• Display-required (Qt/Xvfb) tests:
  • Located in src/airunner/utils/tests/xvfb_required/
  • Require a real Qt display environment (cannot be run headlessly or with pytest-qt)
  • Typical for low-level Qt worker/signal/slot logic
  • Run with:

    xvfb-run -a pytest src/airunner/utils/tests/xvfb_required/
    # Or for a single file:
    xvfb-run -a pytest src/airunner/utils/tests/xvfb_required/test_background_worker.py
    

  • See the README in xvfb_required/ for details.

CI/CD

• By default, only headless-safe tests are run in CI.
• Display-required tests are intended for manual or special-case runs (e.g., when working on Qt threading or background worker code).
• (Optional) You may automate this split in CI by adding a separate job/step for xvfb tests.

General Testing Guidelines

• All new utility code must be accompanied by tests.
• Use pytest, pytest-qt (for GUI), and unittest.mock for mocking dependencies.
• For more details on writing and organizing tests, see the project coding guidelines and the src/airunner/utils/tests/ folder.

Development & Testing

• Follow the copilot-instructions.md for all development, testing, and contribution guidelines.
• Always use the airunner command in the terminal to run the application.
• Always run tests in the terminal (not in the workspace test runner).
• Use pytest and pytest-cov for running tests and checking coverage.
• UI changes must be made in .ui files and rebuilt with airunner-build-ui.

Documentation

• See the Wiki for architecture, usage, and advanced topics.

Module Documentation

• API Service Layer
• Main Window Model Load Balancer
• Facehugger Shield Suite
• NodeGraphQt Vendor Module
• Xvfb-Required Tests
• ORM Models

For additional details, see the Wiki.