langbot-app/langbot

★ 16,016PythonAudience · developerComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((langbot))
    Chat platforms
      Discord Telegram Slack
      WeChat WeCom LINE
      Email Matrix
    AI backends
      OpenAI Anthropic
      Ollama local models
      Dify n8n Langflow
    Features
      RAG knowledge base
      Plugin system
      Admin panel
    Use cases
      Internal assistants
      Community bots
      Customer support

mindmap root((langbot)) Chat platforms Discord Telegram Slack WeChat WeCom LINE Email Matrix AI backends OpenAI Anthropic Ollama local models Dify n8n Langflow Features RAG knowledge base Plugin system Admin panel Use cases Internal assistants Community bots Customer support

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Deploy an internal company assistant on Slack or Lark that answers questions from a knowledge base.

USE CASE 2

Build a community helper bot on Discord or Telegram backed by any cloud or local AI model.

USE CASE 3

Create a customer-facing agent on WeChat or WeCom that handles common support queries.

USE CASE 4

Connect a local Ollama model to multiple chat platforms through a single self-hosted server.

Tech stack

PythonDockerOpenAI SDKOllamaMCP

Getting it running

Difficulty · moderate Time to first run · 30min

Requires configuring at least one LLM API key and a webhook or bot token for your target chat platform.

In plain English

LangBot is an open-source platform for building AI-powered chat bots that live inside instant-messaging apps. The README describes it as a production-grade platform that connects large language models to chat platforms so you can create agents that hold conversations, run tools, and plug into existing workflows. Out of the box it supports Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom (Enterprise WeChat), Lark, DingTalk, KOOK, Satori, Email, and Matrix, which can bridge to networks such as Signal, WhatsApp, and iMessage. A single LangBot server sits between the chat platforms and an AI model of your choice. It integrates with cloud LLMs including OpenAI, Anthropic, DeepSeek, Google Gemini, xAI, Moonshot, and Zhipu AI, with locally-run models through Ollama and LM Studio, and with orchestration stacks like Dify, Coze, n8n, and Langflow. It supports the MCP protocol for connecting tools to models. Conversations can be multi-turn, multi-modal, and streamed, and there is a built-in retrieval-augmented generation feature for grounding answers in a knowledge base. A browser-based management panel lets you configure pipelines, plugins, access control, rate limits, and sensitive-word filtering without editing config files. Hundreds of plugins extend behavior through an event-driven architecture. Someone would reach for LangBot to ship an internal company assistant on Slack or Lark, a community helper on Discord or Telegram, or a customer-facing agent on WeChat. Quick-start options include a one-line uvx command, Docker Compose, one-click deploys to Zeabur or Railway, and a hosted Cloud version. The project is written in Python and supports versions 3.10 through 3.13.

Copy-paste prompts

Prompt 1

I want to deploy LangBot on Docker Compose with a DeepSeek model and connect it to my Discord server. Show me the docker-compose.yml and the channel configuration steps.

Prompt 2

Help me add a retrieval-augmented generation knowledge base to my LangBot instance so it answers questions from my company's internal docs.

Prompt 3

I want to write a LangBot plugin that intercepts incoming messages, calls an external API, and injects the result into the AI's context. Show me the event hook structure.

Prompt 4

Set up a LangBot pipeline that routes messages from Telegram to a locally-running Ollama model and streams the response back to the user.

Prompt 5

Configure LangBot's rate limiting and sensitive-word filtering so my public Discord bot cannot be abused or produce harmful output.

Open on GitHub → Explain another repo

← langbot-app on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.