AstrBot
An open-source AI agent chatbot platform integrating multiple IM apps, LLMs, and plugins.
Build production-ready conversational AI and agent workflows across mainstream messaging platforms.
AstrBot is an open-source all-in-one Agent chatbot platform designed to integrate LLMs, multimodal features, and MCP into instant messaging apps like Telegram, Slack, and Discord. It suits developers and teams looking to quickly deploy custom AI assistants, automated customer service, or knowledge bases within existing chat workflows.
What it is
The platform connects major LLM services and agent platforms like Dify and Coze to over a dozen instant messaging apps and protocols, including QQ, Feishu, DingTalk, and Slack. It features an isolated Agent Sandbox for safe code and shell execution, auto context compression, persona settings, and support for over 1,000 one-click installable plugins.
Who it's for
It suits developers and system administrators seeking an extensible, multi-platform conversational AI framework with native IM bindings and plugin support. It does not suit non-technical users who require a fully managed, zero-configuration cloud service without handling deployments or server management.
Key features
Multi-Platform IM Integration
Connects your AI agents directly to QQ, Telegram, Slack, Discord, Feishu, DingTalk, and other messaging apps.
Isolated Agent Sandbox
Provides a secure environment for isolated execution of code, shell calls, and session-level resource reuse.
Extensive Plugin Ecosystem
Supports one-click installation from a library of over 1,000 community and official plugin extensions.
Broad LLM & STT/TTS Support
Integrates with OpenAI, Anthropic, Gemini, DeepSeek, Ollama, and numerous speech-to-text and text-to-speech services.
Up and running in 3 steps
Our honest verdict
What's great
- Native integration with a massive range of global and regional messaging applications and protocols.
- Built-in agent sandbox allows safe, isolated code execution and shell calls during sessions.
- Extensible architecture supports over 1,000 one-click installable plugins for custom features.
- Compatible with a wide variety of LLM gateways, self-hosted models, and LLMOps platforms like Dify and Coze.
Where it falls short
- Requires technical proficiency with command-line tools, Python environments, or Docker containers to deploy and manage.
- Running underlying LLMs, speech services, or cloud infrastructure incurs external API or hosting costs.
- Initial setup and platform-specific webhook configurations can be complex for non-developers.
Pricing & license
AstrBot is free and open source under its license. There are no software fees, though you will incur costs for self-hosted server infrastructure or external LLM and speech API usage.
Open remote AI-training roles
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
Which messaging platforms are supported?
AstrBot natively supports QQ, Telegram, Slack, Discord, Feishu, DingTalk, WeChat Work, WeChat Official Accounts, LINE, and more through official or community adapters.
How do I deploy AstrBot?
You can deploy it using the `uv` CLI tool, Docker and Docker Compose, pre-built desktop and launcher applications, or cloud partners like RainYun.
Can I connect self-hosted models?
Yes, AstrBot supports self-hosted model backends like Ollama and LM Studio alongside commercial API providers.
