🦞LobsterAI
netease-youdao/LobsterAI · homepage ↗
Open-source, desktop-grade AI agent that gets real work done, data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.
⭐ Popular: 6k stars, gaining about 57 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Packages data analysis, document, slide, and video generation, plus web research into a single desktop agent that runs against local files, the terminal, and the browser rather than a cloud sandbox.
- Ships with 28 built-in skills covering Word, Excel, PowerPoint, PDF, web search, browser automation, and email, and extends through MCP servers, so users get a broad task set without wiring up tools themselves.
- Adds remote control from WeChat, WeCom, DingTalk, Feishu, QQ, Telegram, Discord, and email, letting users trigger agent work from the messaging apps they already use.
under the hood
- Split into two layers: Cowork handles persistence, permissions, UI state, artifacts, memory, and messaging bindings, while the OpenClaw runtime handles agent execution.
- Built as an Electron 40 desktop app with a React 18, Redux Toolkit, and Tailwind front end, SQLite for local storage, and Vite plus Vitest for build and test.
- Primarily TypeScript with some JavaScript, Python, and Shell, distributed as native macOS and Windows installers under an MIT license from NetEase Youdao.
Radar summary, generated from the project's public sources
star history
- PR#28 2k 2026-02-25
- now 6k + 4k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Deep in the understory, shipping hard, still flying under the radar.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Modular AI agent experimentation framework
similar projects
compare these →- 🎛️ CopilotKit
6.2× the stars
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
37k ACTIVE - 🤖 nanobot
Python · 8× the stars
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
47k ACTIVE - 📖 ai-agent-book
Python · 6.4× the stars
AI Agent PDF
38k ACTIVE
comments
Sign in with GitHub to add your blip on LobsterAI.