Repolode
Submit
yincongcyincong

yincongcyincong/MuseBot

A Go chat bot that connects Telegram, Discord, Slack, Lark, DingTalk, WeCom, QQ and WeChat to LLMs such as OpenAI, Gemini and DeepSeek.

View on GitHubWebsite
Stars
1,742
Forks
254
Open issues
3
Last commit
5 hours ago

What is it?

MuseBot is a chat bot written in Go that relays messages from communication apps to large language model APIs and returns the replies. It supports Telegram, Discord, Slack, Lark (Feishu), DingTalk, WeCom, QQ and WeChat, and can route requests to OpenAI, Gemini, DeepSeek, Doubao, Qwen, OpenRouter and several other providers, including custom endpoints.

Beyond text chat, the bot handles image input and generation, document questions for txt, pdf, csv and html files, voice input, and video generation, depending on the configured model. It also offers streaming replies, per-user token limits, MCP-based function calling, RAG context, scheduled cron triggers, and a Web API. Configuration is done through environment variables or command-line flags, with SQLite or MySQL for storage.

The project can be run directly with go run or deployed with Docker, and it works in both private chats and group chats.

Key features

  • 01Connects to Telegram, Discord, Slack, Lark, DingTalk, WeCom, QQ and WeChat.
  • 02Routes requests to OpenAI, Gemini, DeepSeek, Doubao, Qwen, OpenRouter and other LLM providers.
  • 03Supports image recognition, document Q&A, voice input and media generation, depending on the model.
  • 04Streams responses in real time and keeps per-conversation context.
  • 05Offers MCP-based function calling, RAG, cron triggers and a Web API.
  • 06Stores data in SQLite or MySQL and can be deployed with Docker.

Use cases

  • Adding an AI assistant to a team's Slack or Lark workspace.
  • Running a private Telegram or Discord bot backed by your own API keys.
  • Providing a Chinese-platform AI bot for DingTalk, WeCom or WeChat users.
  • Building a custom frontend on top of the bot's Web API.

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/yincongcyincong/MuseBot.git
  2. 2

    Install dependencies

    go mod tidy
  3. 3

    Run the bot locally with your tokens

    go run main.go -telegram_bot_token=telegram-bot-token -deepseek_token=deepseek-auth-token

Things to know

  • You need a bot token from each chat platform you want to use, plus an LLM API key such as DeepSeek.
  • Enterprise platforms like WeCom, DingTalk, QQ and WeChat need separate app setup and callback configuration.

Topics

#ai-bot#llm#chatbot#telegram#discord#slack#feishu#openai#deepseek#golang

FAQ

What is MuseBot?
A Go chat bot that connects Telegram, Discord, Slack, Lark, DingTalk, WeCom, QQ and WeChat to LLMs such as OpenAI, Gemini and DeepSeek. MuseBot is a chat bot written in Go that relays messages from communication apps to large language model APIs and returns the replies. It supports Telegram, Discord, Slack, Lark (Feishu), DingTalk, WeCom, QQ and WeChat, and can route requests to OpenAI, Gemini, DeepSeek, Doubao, Qwen, OpenRouter and several other providers, including custom endpoints.
Is MuseBot free to use? What license does it have?
MuseBot is open source under the MIT license. Check the license terms before using it in commercial products.
Is MuseBot still maintained?
Actively maintained. The last commit to MuseBot was on Oct 20, 2026.
What can I use MuseBot for?
Adding an AI assistant to a team's Slack or Lark workspace. Running a private Telegram or Discord bot backed by your own API keys. Providing a Chinese-platform AI bot for DingTalk, WeCom or WeChat users. Building a custom frontend on top of the bot's Web API.
How do I install MuseBot?
Clone the repository: git clone https://github.com/yincongcyincong/MuseBot.git Install dependencies: go mod tidy Run the bot locally with your tokens: go run main.go -telegram_bot_token=telegram-bot-token -deepseek_token=deepseek-auth-token
Where can I get MuseBot?
The source code and installation instructions are on GitHub: https://github.com/yincongcyincong/MuseBot

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects