langbot-app/LangBot

Project overview

A platform for building, debugging, and shipping agentic instant messaging bots that connect LLMs to chat platforms. It uses one codebase to support Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, and KOOK, managed via a browser panel or API.

Project type

MCP · AI Agent · RAG

Use cases

Knowledge Q&A · Automation

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• Developers and enterprise teams building agentic instant messaging bots for AI customer service and automation across multiple platforms.

Key capabilities

• Uses one codebase to support bots on Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, and KOOK.
• Provides a built-in RAG knowledge base for bot conversations and agents.
• Provides access control, rate limiting, sensitive-word filtering, monitoring, and exception handling.
• Provides plugins, event-driven architecture, component extensions, and MCP protocol support.
• Lets users configure, manage, and monitor bots in a browser interface without YAML editing.
• Exposes an MCP endpoint that mirrors the HTTP API for programmatic management of bots, pipelines, plugins, and models.

Limitations and risks

• The public demo environment should not be used for sensitive information.
• Entering sensitive information into the public demo environment risks exposing that information.
• GPU, data boundary, cost dependency, coding requirements, telemetry, minimum hardware, OS, databases, external services, and model requirements are not documented.

Getting started

• Run `uvx langbot` and visit http://localhost:5300 to configure and manage bots without YAML editing.

Evidence and sources

• README: LangBot is an **open-source, production-grade platform** for building AI-powered instant messaging bots. It connects Large Language Models (LLMs) to any chat platform, enabling yo…
• README: - **Universal IM Platform Support** — One codebase for Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
• README: - **AI Conversations & Agents** — Multi-turn dialogues, tool calling, multi-modal support, streaming output. Built-in RAG (knowledge base) with deep integration to [Dify](https://…
• README: - **Production-Ready** — Access control, rate limiting, sensitive word filtering, comprehensive monitoring, and exception handling. Trusted by enterprises.
• README: - **Plugin Ecosystem** — Hundreds of plugins, event-driven architecture, component extensions, and [MCP protocol](https://modelcontextprotocol.io/) support.

Reviewed at: 2026-07-17T13:54:09Z