LangBot is a platform for building, debugging, and shipping agentic instant messaging bots across chat platforms using one codebase. It provides a web management panel, a built-in RAG knowledge base, and an MCP endpoint for programmatic management.
Project overview
The project supports multiple chat platforms from a single codebase and includes a built-in MCP endpoint that mirrors its HTTP API for programmatic bot, pipeline, plugin, and model management.
Project type
RAG · Workflow · Model Runtime
Use cases
Knowledge Q&A
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers and enterprise teams building and shipping agentic instant messaging bots across multiple chat platforms.
Teams requiring a web interface to configure, manage, and monitor bots without YAML editing.
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, operating system, database, external service, minimum hardware, model requirements, and telemetry are not documented.
Getting started
Setup is documented as easy due to a one-line launch command. Run `uvx langbot` and visit http://localhost:5300 to begin.
Alternatives and comparisons
Provides building blocks for multi-modal AI agents that watch, listen, and understand real-time video and voice with ultra-low latency.
An open-source .NET framework with modular components for building AI bots and managing multi-agent scenarios.
A Go-native stack providing LLM agents, graph workflows, memory, and tool calling for concurrent agent systems.