langbot-app/LangBot

Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow

What is it? LangBot is an open-source, production-grade platform for building AI-powered instant messaging (IM) bots. It bridges Large Language Models (LLMs) to chat platforms like Slack, Discord, Telegram, WeChat, and 10+ others, allowing you to create intelligent agents that converse and execute tasks—all managed from a single web dashboard.

Core capabilities:

  • AI & Agents: Multi-turn dialogues, tool calling, multi-modal support, streaming output, and built-in RAG (knowledge base) with deep integrations to Dify, Coze, n8n, Langflow, etc.
  • Universal IM Support: One codebase works across Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK, and Matrix (the latter bridging to WhatsApp, Signal, etc.).
  • Production-Ready: Access control, rate limiting, sensitive-word filtering, monitoring, and exception handling.
  • Plugin Ecosystem: Event-driven architecture with hundreds of plugins and Model Context Protocol (MCP) support.
  • Web Management: Configure, manage, and monitor bots via a browser UI—no YAML editing required.

Why it's notable (Agent-friendly design): LangBot is explicitly built so that AI coding agents (Claude Code, Codex, Copilot) can operate and extend it. It exposes a built-in MCP server at /mcp, offers a CLI (lbctl, a separate repo) to manage bots/pipelines/models programmatically, and ships a skills/ directory as the 'single source of truth' for agents to learn how to build on it.

How to run:

  • One-liner: uvx langbot (requires uv, opens on localhost:5300)
  • Docker Compose: git clone repo, then cd docker && docker compose --profile all up -d
  • Cloud: LangBot Cloud or one-click deploys to Zeabur/Railway.

Supported Models: Works with OpenAI, Anthropic, DeepSeek, Gemini, xAI, Moonshot, Zhipu, local models via Ollama/LM Studio, plus gateways like SiliconFlow and Aliyun Bailian. It supports 15+ LLM providers and integrations.

Related

  • Project
    AstrBotDevs/AstrBot

    AstrBot is an open-source agent chatbot platform that connects LLMs to various instant messaging apps, featuring a plugin system, secure sandbox execution, and support for multiple AI model providers.

  • 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
    LangChat/langchat

    An open-source AI Agent application platform that integrates model management, RAG, and tool extensions to help developers quickly build and deploy AI applications.

  • 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
    agentconnect-md/agentconnect

    AgentConnect is an open‑source, self‑hosted platform that lets teams run many AI agents (Claude Code, OpenAI Codex, Grok Build, etc.) inside Slack, Discord, Telegram, Google Chat, GitHub, GitLab, Linear and other tools. Agents can call each other, keep memory, be routed by Jev, and act on webhooks or schedules. The system consists of Daemons (run agents), an optional Relay, and a Control‑Plane UI for config, auth and observability. It ships via Docker‑Compose for local use and a Helm chart for Kubernetes, all under Apache‑2.0.