workflowstacks
mcp-server

neo: Self‑evolving AI team engine for live apps

Deploy an AI‑powered, self‑healing multi‑agent system that integrates Neural Link, GraphRAG and DreamService, letting founders automate complex app intelligence. 3.3k+ GitHub stars.

From the repo · “Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.”

intermediate⏱ 1-2 hours💵 Free + LLM API costs
3,294 stars+1★ this week258 forksJavaScriptGuide quality 9/10 · reviewed Oct 19Updated 10/21/2026100% free · open source
What it is

Use Neo to integrate your AI model with web applications and tools.

Real use case example

"A founder wants to automate customer onboarding for her new Stripe-integrated SaaS. She uses Neo to create a flow that connects Stripe with Notion, saving her time and improving customer experience."

Best insideCursorClaude DesktopContinueSelf-hosted
When to use it
  • •When building a complex AI-powered application that requires a high degree of autonomy and self-healing
  • •When needing to integrate multiple AI models and services into a single application
  • •When requiring a scalable and adaptable AI solution that can evolve with the needs of the application
Ready-to-paste prompt
neo.dreamService.generateText({ prompt: 'Generate a product description for a new smartwatch', length: 200 });
Heads up: Make sure to configure the Neural Link correctly, as it requires a specific set of dependencies and environment variables to be set, such as `NEURAL_LINK_API_KEY` and `NEURAL_LINK_API_SECRET`
Saves to your device
Use with Claude
New

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

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/neo && curl -fsSL https://workflowstacks.com/api/skills/neo/claude-skill -o ~/.claude/skills/neo/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 neo: Self‑evolving AI team engine for live apps works
Codeflow
Free to inspect

Neo: Self‑evolving AI team engine for live apps is a very large JavaScript project (~248k lines across 1357 code files, plus 739 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~248k lines · 1357 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Node.js
No API keys detected
JavaScript 96%SCSS 4%
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
    src/Main.mjs
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
  5. 5
    src/index.js
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic503 files
apps/Sub-packages / plugins1563 files
examples/Examples you can copy714 files
docs/Documentation32 files
resources/Folder1848 files
learn/Folder149 files
buildScripts/Folder99 files
test/Tests — proof it works811 files
READMEHas testsDocumentedCI checksExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
neomjs
Language
JavaScript
Category
mcp-server
Published
11/10/2019

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/neo.svg)](https://workflowstacks.com/skills/neo?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

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

MCP config

Brave Search MCP config

Give Claude live web search via the Brave Search API.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 355,695
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,361
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★ 131,266
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★ 313
DashClaw: Enforce AI Agent Policies and Get Auditable Decisions
DashClaw lets founders control AI agents with guard policies, approval workflows, and built‑in audit trails—perfect for regulated AI ops.
mcp-server★ 455
Evolve Java SDLC with cursor-rules-java
Get reusable AI workflow for modern Java Enterprise. For founders and Java developers.
mcp-server★ 28,639
qwen-code: Supercharge Your Terminal with an AI Coding Agent
Boost developer productivity by running an AI-powered coding assistant directly in your terminal. Ideal for founders who need fast, context-aware code generation without leaving the CLI.