mcp-server

LobsterAI: Automate Tasks

Get automated data analysis and research with LobsterAI, a desktop-grade AI agent, ideal.
5,920 stars937 forksTypeScriptGuide quality 8/10Updated 8/18/2026100% 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: Automate Tasks works
Codeflow
Free to inspect

LobsterAI: Automate Tasks is a very large TypeScript project (~316k lines across 1455 code files, plus 43 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
~316k lines · 1455 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 logic1329 files
SKILLs/Prompts, skills & agent definitions370 files
docs/Documentation46 files
scripts/Helper scripts144 files
openclaw-extensions/Folder19 files
resources/Folder11 files
patches/Patches1 files
specs/Tests — proof it works195 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? Claim your listing → and earn 85% of every sale.