group

telegram-group: https://t.me/+WtaMcDpaMOlhZTE1 , or you can have a try robot GWSbot. every body have 10000 token to try this bot, please give me a star!

QQ群：1031411708

MuseBot

This repository provides a Telegram, Disccord bot built with Golang that integrates with LLM API to provide AI-powered responses. The bot supports openai deepseek gemini openrouter LLMs, making interactions feel more natural and dynamic. 中文文档

Usage Video

deepseek: https://www.youtube.com/watch?v=kPtNdLjKVn0
gemini: https://www.youtube.com/watch?v=7mV9RYvdE6I
chatgpt: https://www.youtube.com/watch?v=G_DZYMvd5Ug

🚀 Features

• 🤖 AI Responses: Uses DeepSeek API for chatbot replies.
• ⏳ Streaming Output: Sends responses in real-time to improve user experience.
• 🏗 Easy Deployment: Run locally or deploy to a cloud server.
• 👀 Identify Image: use image to communicate with deepseek, see doc.
• 🎺 Support Voice: use voice to communicate with deepseek, see doc.
• 🐂 Function Call: transform mcp protocol to function call, see doc.
• 🌊 RAG: Support Rag to fill context, see doc.
• 🌞 AdminPlatform: Use platform to manage MuseBot, see doc.
• 🌛 Register: With the service registration module, robot instances can be automatically registered to the registration center doc

📸 Support Platform

Platform	Supported	Description	Docs / Links
🟦 Telegram	✅	Supports Telegram bot (go-telegram-bot-api based, handles commands, inline buttons, ForceReply, etc.)	Docs
🌈 Discord	✅	Supports Discord bot	Docs
🌛 Web API	✅	Provides HTTP/Web API for interacting with LLM (great for custom frontends/backends)	Docs
🔷 Slack	✅	Supports Slack (Socket Mode / Events API / Block Kit interactions)	Docs
🟣 Lark (Feishu)	✅	Supports Lark long connection & message handling (based on larksuite SDK, with image/audio download & message update)	Docs
🆙 DingDing	✅	Supports Dingding long connection	Docs
⚡️ Work WeChat	✅	Support Work WeChat http callback to trigger LLM	Docs
🌞 QQ	✅	Support QQ http callback to trigger LLM	Docs
🚇 Wechat	✅	Support Wechat http callback to trigger LLM	Docs

Supported Large Language Models

Model	Provider	Text Generation	Image Generation	Video Generation
🌟 Gemini	Google	✅	✅	✅
💬 ChatGPT	OpenAI	✅	✅	❌
🐦 Doubao	ByteDance	✅	✅	✅
🧠 DeepSeek	DeepSeek	✅	❌	❌
🌐 OpenRouter	OpenRouter	✅	✅	✅

🤖 Text Example

🎺 Multimodal Example

📌 Requirements

• Go 1.24+
• Telegram Bot Token
• DeepSeek Auth Token

📥 Installation

1. Clone the repository

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

2. Install dependencies

    go mod tidy

3. Set up environment variables

    export TELEGRAM_BOT_TOKEN="your_telegram_bot_token"
    export DEEPSEEK_TOKEN="your_deepseek_api_key"

🚀 Usage

Run the bot locally:

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

Use docker

  docker pull jackyin0822/musebot:latest
  docker run -d -v /home/user/data:/app/data -e TELEGRAM_BOT_TOKEN="telegram-bot-token" -e DEEPSEEK_TOKEN="deepseek-auth-token" --name my-telegram-bot  jackyin0822/MuseBot:latest

⚙️ Configuration

You can configure the bot via environment variables:

Variable Name	Description	Default Value
TELEGRAM_BOT_TOKEN (required)	Your Telegram bot token	-
DEEPSEEK_TOKEN (required)	DeepSeek Api Key	-
OPENAI_TOKEN	Open AI Token	-
GEMINI_TOKEN	Gemini Token	-
OPEN_ROUTER_TOKEN	OpenRouter Token doc	-
VOL_TOKEN	Vol Token doc	-
CUSTOM_URL	custom deepseek url	https://api.deepseek.com/
TYPE	deepseek/openai/gemini/openrouter/vol	deepseek
VOLC_AK	volcengine photo model ak doc	-
VOLC_SK	volcengine photo model sk doc	-
Ernie_AK	ernie ak doc	-
Ernie_SK	ernie sk doc	-
DB_TYPE	sqlite3 / mysql	sqlite3
DB_CONF	./data/telegram_bot.db / root:admin@tcp(127.0.0.1:3306)/dbname?charset=utf8mb4&parseTime=True&loc=Local	./data/telegram_bot.db
ALLOWED_USER_IDS	user id, only these users can use bot, using "," splite. empty means all use can use it. 0 means all user is banned	-
ALLOWED_GROUP_IDS	chat id, only these chat can use bot, using "," splite. empty means all group can use it. 0 means all group is banned	-
DEEPSEEK_PROXY	deepseek proxy	-
TELEGRAM_PROXY	telegram proxy	-
LANG	en / zh	en
TOKEN_PER_USER	The tokens that each user can use	10000
ADMIN_USER_IDS	admin user, can use some admin commands	-
NEED_AT_BOT	is it necessary to trigger an at robot in the group	false
MAX_USER_CHAT	max existing chat per user	2
VIDEO_TOKEN	volcengine Api keydoc	-
HTTP_PORT	http server port	36060
USE_TOOLS	if normal conversation use function call tools or not	false
CA_FILE	http server ca file	-
CRT_FILE	http server crt file	-
KEY_FILE	http server key file	-
MEDIA_TYPE	openai/gemini/vol create photo or video	vol
MAX_QA_PAIR	how many question and answer pairs as context	15
CHARACTER	background character	-

CUSTOM_URL

If you are using a self-deployed DeepSeek, you can set CUSTOM_URL to route requests to your self-deployed DeepSeek.

DEEPSEEK_TYPE

deepseek: directly use deepseek service. but it's not very stable others: see doc

DB_TYPE

support sqlite3 or mysql

DB_CONF

if DB_TYPE is sqlite3, give a file path, such as ./data/telegram_bot.db if DB_TYPE is mysql, give a mysql link, such as root:admin@tcp(127.0.0.1:3306)/dbname?charset=utf8mb4&parseTime=True&loc=Local, database must be created.

LANG

choose a language for bot, English (en), Chinese (zh), Russian (ru).

other config

deepseek_conf photo_conf video_conf audio_conf

Command

/clear

clear all of your communication record with deepseek. this record use for helping deepseek to understand the context.

/retry

retry last question.

/mode

chose deepseek mode, include chat, coder, reasoner chat and coder means DeepSeek-V3, reasoner means DeepSeek-R1.

/balance

/state

calculate one user token usage.

/photo /edit_photo

using volcengine photo model create photo, deepseek don't support to create photo now. VOLC_AK and VOLC_SK is necessary.doc

/edit_photo will update you photo base on your description.

/video

create video. DEEPSEEK_TOKEN must be volcengine Api key. deepseek don't support to create video now. doc

/chat

allows the bot to chat through /chat command in groups, without the bot being set as admin of the group.

/help

/task

multi agent communicate with each other!

/change_photo

only for tencent app (wechat, qq, work wechat)
change photo base on your prompt.

/rec_photo

only for tencent app (wechat, qq, work wechat)
recognize photo base on your prompt.

Deployment

Deploy with Docker

1. Build the Docker image

    docker build -t deepseek-telegram-bot .

2. Run the container

     docker run -d -v /home/user/xxx/data:/app/data -e TELEGRAM_BOT_TOKEN="telegram-bot-token" -e DEEPSEEK_TOKEN="deepseek-auth-token" --name my-telegram-bot MuseBot

Contributing

Feel free to submit issues and pull requests to improve this bot. 🚀

License

MIT License © 2025 jack yin