AstrBotDevs/AstrBot

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

What it solves

AstrBot provides a unified infrastructure to connect powerful AI models to various instant messaging platforms. It solves the fragmentation problem for developers and users who want to deploy intelligent agents across different chat apps (like Telegram, WeChat, QQ, or Slack) without building custom integrations for each one.

How it works

AstrBot acts as a middleware platform that bridges messaging protocols with LLM providers. It supports a wide array of AI services, including direct LLM APIs (OpenAI, DeepSeek, etc.), agent-building platforms (Dify, Coze), and specialized speech-to-text or text-to-speech services. The platform features a plugin system for extensibility, an agent sandbox for secure code execution, and automatic context management to keep conversations coherent.

Who it’s for

It is designed for individuals, developers, and teams who want to build and deploy AI companions, customer service bots, or automation assistants within their existing communication workflows.

Highlights

  • Multi-Platform Support: Connects to over 15 messaging services including Telegram, Slack, Discord, and various enterprise communication tools.
  • Extensible Ecosystem: Access to 1000+ community-contributed plugins for one-click installation.
  • Secure Execution: Includes an Agent Sandbox for safely running code and shell commands during agent interactions.
  • Flexible Deployment: Supports various methods including Docker, CLI (via uv), and one-click cloud deployment options.
  • Broad Model Compatibility: Integrates with major LLM providers, local inference engines like Ollama, and LLMOps platforms like Dify and Coze.

Related

  • Project
    langbot-app/LangBot

    Open-source platform that unifies LLMs (OpenAI, DeepSeek, local Ollama, etc.) into AI agents deployable across Slack, Discord, Telegram, WeChat, QQ, and more—with a web dashboard, plugin marketplace, and MCP/CLI tools so human or AI developers can manage every bot from one place.

  • Project
    KroMiose/nekro-agent

    A highly extensible AI bot framework that enables LLMs to execute code in secure sandboxes and interact across multiple chat platforms via a unified adapter architecture.

  • Project
    HKUDS/nanobot

    An ultra-lightweight, self-hosted personal AI agent framework that integrates multiple LLM providers, long-term memory, and various chat apps into a single runtime.

  • Project
    countbot-ai/CountBot

    CountBot is a Python-based, MIT-licensed AI work assistant that runs on your own server, connects to the chat apps you already use (Lark, WeChat, QQ, Telegram, etc.), and can execute real work: run skills on schedules, split tasks across multi-agent teams, use 22 model providers, and deliver results to your chosen channels.

  • Project
    photon-hq/spectrum-ts

    Spectrum‑ts is a TypeScript SDK for building AI agents that operate over real‑world messaging channels (iMessage, SMS, email, Slack, Telegram, etc.). It provides a unified, async‑iterator API, built‑in providers for major platforms, optional hosted infrastructure, and graceful startup cancellation. Install with `bun add spectrum-ts`, supply a Photon project ID/secret, and write a simple loop that replies to incoming messages.