LiangNiang

LiangNiang / OpenMantis

Public

Lightweight multi-platform AI agent chat framework. Connect multiple LLMs to Feishu/WeCom/QQ with composable tools, long-term memory, scheduling & browser automation. | 轻量级多平台 AI Agent 聊天框架，连接多个 LLM 到飞书/企业微信/QQ，支持可组合工具、长期记忆、定时任务和浏览器自动化。

88
6
100% credibility
Found Apr 15, 2026 at 29 stars 3x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

OpenMantis connects AI models to chat platforms like Feishu, WeCom, and QQ with tools for automation, scheduling, browser control, and a web dashboard for easy setup.

How It Works

1
📥 Download the app

Grab the ready-to-run program for your computer from the releases page—no setup needed.

2
🚀 Start it up

Run the simple command to launch your AI assistant and watch the setup helper open in your browser.

3
🧙 Set up your helper

Follow the friendly wizard to pick your AI brain and connect your chat apps like Feishu or WeCom.

4
🔧 Pick your tools

Choose extras like web search, file handling, or scheduling so your assistant can do more.

5
✅ Hit launch

Click to make it live—one restart and your AI is chatting in your messaging apps.

💬 Chat away

Send messages in Feishu, WeCom, or QQ—your smart assistant replies with tools, memory, and voice if you want.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 29 to 88 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is OpenMantis?

OpenMantis is a lightweight TypeScript agent framework that connects multiple LLMs to Feishu, WeCom, and QQ for chat-based automation. It delivers composable tools like bash execution, web search, file I/O, RSS parsing, TTS, and browser control, plus long-term memory and cron scheduling—all via pre-built binaries or Bun runtime. Users get a web dashboard for setup, slash commands for session management, and streaming replies in chats.

Why is it gaining traction?

It stands out as a lightweight GitHub agent solution for Chinese platforms, skipping heavy deps with standalone executables and native streaming cards. Devs hook into real browser automation or scheduled tasks without custom infra, and channel-specific tools (like Feishu file uploads) make agents feel integrated. Multi-LLM switching per chat keeps costs flexible.

Who should use this?

Ops teams or internal tool builders on Feishu/WeCom/QQ needing chat agents for reminders, data scraping, or lightweight RAG workflows. Suits solo devs prototyping browser automation or memory-driven bots without Docker sprawl.

Verdict

Early at 11 stars and 1.0% credibility score, but solid README, binaries, and CLI make it instantly usable—docs cover edge cases like macOS quarantine. Grab a release for Feishu/WeCom/QQ agent experiments; monitor for multi-agent roadmap.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.