workflowstacks
mcp-server

LobsterAI: Turn Your Desktop into an AI Workhorse for Founders

Command data analysis, slide decks, docs, video and web research from your phone via WeChat, Feishu, DingTalk or Telegram—desktop‑grade AI at your fingertips. 6.1k+ GitHub stars

From the repo · “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.”

6,138 stars+25★ this week979 forksTypeScriptGuide quality 9/10 · reviewed Oct 19Updated 10/22/2026100% free · open source
What it does

LobsterAI is a desktop-grade AI agent that automates data analysis, research, and document creation, allowing startup founders to streamline their workflow and increase productivity.

When to use it
  • •When you need to analyze large datasets and generate insights quickly
  • •When creating presentation slides, documents, or videos requires extensive research
  • •When you want to leverage AI-powered tools on your desktop and control them remotely via messaging apps
Ready-to-paste prompt
!research 'market trends in AI-powered startup tools' --slides --docs
Heads up: You need to have Node.js (version 16 or higher) and TypeScript installed on your system to run LobsterAI, and ensure you have the necessary dependencies installed before starting the server
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/lobsterai && curl -fsSL https://workflowstacks.com/api/skills/lobsterai/claude-skill -o ~/.claude/skills/lobsterai/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How LobsterAI: Turn Your Desktop into an AI Workhorse for Founders works
Codeflow
Free to inspect

LobsterAI: Turn Your Desktop into an AI Workhorse for Founders is a very large TypeScript project (~355k lines across 1669 code files, plus 70 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~355k lines · 1669 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
Needs API keys (.env)
TypeScript 89%JavaScript 6%Python 3%NSIS 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    package.json
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    src/main/main.ts
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic1536 files
SKILLs/Prompts, skills & agent definitions370 files
docs/Documentation49 files
scripts/Helper scripts216 files
openclaw-extensions/Folder19 files
resources/Folder11 files
patches/Patches1 files
specs/Tests — proof it works232 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
netease-youdao
Language
TypeScript
Category
mcp-server
Published
2/12/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/lobsterai.svg)](https://workflowstacks.com/skills/lobsterai?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Context7 (live docs) MCP config

Pull up-to-date library docs into Claude so it codes against the real API.

Free n8n template

AI Support Agent (Chat)

A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.

MCP config

Playwright (browser) MCP config

Drive a real browser for testing and automation from Claude.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 362,094
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,432
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 132,268
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 23,009
MaxKB: Build Enterprise‑Grade AI Agents Faster
MaxKB lets founders create powerful, scalable AI agents with built‑in knowledge‑base and RAG support. Ideal for Python teams seeking robust, open‑source solutions. 23k+ GitHub stars.
mcp-server★ 511
opencode-swarm: Fast‑track architecture with AI swarm orchestration
Founders can harness a hub‑and‑spoke AI swarm to consult SMEs, auto‑generate code, and run QA reviews, streamlining software engineering from concept to launch.
mcp-server★ 20,104
easy-vibe – Quickly teach coding with a modern beginner course
With 20k+ GitHub stars, easy-vibe lets founders quickly upskill non‑technical staff through a step‑by‑step JavaScript coding tutorial built for low‑code/no‑code workflows.