Project screenshots
Overview
AstrBot provides scalable conversational AI infrastructure designed for individuals, developers, and teams. It functions as a unified bridge connecting various instant messaging (IM) platforms with diverse LLM services and agent platforms. The framework supports multimodal conversations, agent workflows, MCP (Model Context Protocol), skills, knowledge base integration, persona settings, and automatic context compression. It includes a WebUI for management, a Web ChatUI with a built-in agent sandbox and web search, and supports internationalization (i18n).
Key features
- Free and Open Source (AGPL-3.0)
- AI LLM Conversations with Multimodal support
- Agent, MCP, Skills, and Knowledge Base integration
- Persona Settings and Auto Context Compression
- Multi-Platform IM Integration (QQ, Telegram, WeChat Work, Feishu, DingTalk, Slack, Discord, etc.)
- Plugin Extensions with 1000+ community plugins
- Agent Sandbox for isolated code and shell execution
- WebUI and Web ChatUI support
- Internationalization (i18n) Support
- Integration with Dify, Alibaba Cloud Bailian, and Coze
Requirements, installation and quick start
1. uv One-Click Deployment: `uv tool install astrbot --python 3.12`, then `astrbot init`, then `astrbot run`.
2. Docker Deployment: Refer to the official documentation for Docker/Docker Compose instructions.
3. Desktop Application: Download AstrBot-desktop from the AstrBotDevs GitHub organization.
4. Launcher Deployment: Download AstrBot Launcher from GitHub.
5. AUR (Arch Linux): Install via `yay -S astrbot-git`.
6. Cloud Deployment: One-click deployment available via RainYun or Replit.
7. Panel Deployments: Supported via BT-Panel, 1Panel, and CasaOS.
Usage
Model compatibility and use cases
Supports OpenAI and compatible services, Anthropic, Google Gemini, Moonshot AI, Zhipu AI, DeepSeek, Ollama, LM Studio, AIHubMix, CompShare, 302.AI, TokenPony, SiliconFlow, PPIO Cloud, ModelScope, and OneAPI. Also integrates with LLMOps platforms like Dify, Alibaba Cloud Bailian Applications, and Coze. Speech-to-Text supported via OpenAI Whisper, SenseVoice, and Xiaomi MiMo Omni. Text-to-Speech supported via OpenAI TTS, Gemini TTS, GPT-Sovits, FishAudio, Edge TTS, Azure TTS, Minimax TTS, and others.
License and risk notes
Licensed under the GNU Affero General Public License v3.0 (AGPL-3.0).
Editorial verification 2026-08-09: repository URL, owner, description, license and repository statistics were reviewed. License metadata: AGPL-3.0. README was fetched for the channel draft; re-check repository dependencies, releases and model terms before production use.
Release and maintenance
Not stated in the repository metadata.