AstrBot

AstrBot brings AI assistants into messaging apps such as Telegram, Discord, Slack, QQ and WeCom. It's an open source platform under AGPL-3.0 for people building personal companions, customer support bots or team automation. You can run it on your own computer or server, including through Docker, or use its desktop app for browser-style chat.

Model choice is flexible. AstrBot connects to self-hosted Ollama and LM Studio, as well as OpenAI, Anthropic, Google Gemini and OpenAI-compatible services. The assistant platform can run on your hardware while cloud providers process model requests remotely. RainYun also offers cloud deployment for people who don't want to manage a server.

Its agents can call tools, delegate work to sub-agents and carry out workflows. MCP and Skills support connect them to external capabilities, while scheduled jobs handle future tasks. An agent sandbox isolates code execution and shell calls. You can interrupt tasks or change their prompts during execution, and automatic context compression helps manage conversation history.

For document-based answers, AstrBot parses PDF, DOCX and Markdown through Microsoft Markitdown. Its knowledge bases combine semantic search with BM25 keyword retrieval, with support for Chinese and multilingual content. A conversation can draw on multiple knowledge bases.

Plugins extend the platform with long-term memory, user profiles and proactive messages. Persona settings shape how a bot responds. AstrBot also supports image understanding, speech recognition and speech output, and connects to Dify, Alibaba Cloud Bailian and Coze.