tuchg/Lucarne

240 stars · Last commit 2026-05-28

Stop babysitting local AI agents. Just notifications, approve, and resume your Codex,Pi, or Claude code sessions anywhere. 0-Intrusion mobile control bridge via Telegram/Wechat/飞书. No hooks, no skills, no MCP.

README preview

![Lucarne AI Poster](docs/assets/lucarne-ai-poster.png)

[![Release](https://github.com/tuchg/Lucarne/actions/workflows/release.yml/badge.svg)](https://github.com/tuchg/Lucarne/actions/workflows/release.yml)
![Coverage](https://img.shields.io/badge/coverage-67%2F67%20journeys-blue)
![License: MIT](https://img.shields.io/badge/license-MIT-blue)
![Telegram](https://img.shields.io/badge/channel-Telegram-26A5E4?logo=telegram)
![WeChat](https://img.shields.io/badge/channel-WeChat-07C160?logo=wechat)

English | [中文](README.cn.md)

**Stop babysitting your local AI agents.**

- No new mobile app required; receive timely, secure notifications through existing channels
- Zero-intrusion setup: no hooks, no skills, no MCP, no project changes; scan a QR code and start using it in one step
- Agents run on your local computer, so you can step away while WeChat / Telegram keep you synced on key progress
- Permission approvals, clarifying questions, and failure notifications become actionable mobile events
- Scan a WeChat QR code to receive agent messages; quote a message to continue the matching context automatically
- Use the Telegram console to view all agents, workspaces, and historical sessions
- View local agent session history and agents currently running on this machine

View full repository on GitHub →