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, Moonshot, openclaw / hermes agent, deerflow

What it solves

LangBot solves the complexity of connecting Large Language Models (LLMs) to various instant messaging platforms. It provides a unified way to build, debug, and ship intelligent agents to services like Slack, Discord, Telegram, and WeChat without needing to write custom code for every individual platform.

How it works

The platform uses a multi-pipeline architecture to manage different bots for various scenarios. It connects LLM providers (like OpenAI, Anthropic, or local models via Ollama) to chat platforms through a single codebase. It features a web management panel for configuration and monitoring, and supports the Model Context Protocol (MCP) to allow coding agents to programmatically manage bots and plugins.

Who it’s for

  • Enterprises looking for production-ready AI bots with access control and monitoring.
  • Developers wanting to deploy multi-platform AI bots quickly using a single codebase.
  • Community Managers needing AI-powered content filtering and interaction on platforms like Discord or QQ.
  • Workflow Automators wanting to connect tools like n8n or Dify to enterprise messaging apps like Lark or DingTalk.

Highlights

  • Universal IM Support: Connects to Discord, Telegram, Slack, LINE, WeChat, Lark, DingTalk, and more.
  • Agentic Features: Supports multi-turn dialogues, tool calling, multi-modal support, and streaming output.
  • Extensive Integrations: Built-in RAG capabilities and integration with LLMOps tools like Dify and Coze.
  • Plugin Ecosystem: Features an event-driven architecture with hundreds of plugins and MCP support.