neo
Neo.mjs is a self-evolving software organism providing end-to-end AI engineering capabilities through a multi-model cluster.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 3.2k
- Source
- mcp-github
- Repository
- github.com/neomjs/neo
Overview
Neo.mjs is a self-evolving software organism that runs in real-time applications via a multi-model cluster (such as Claude, Gemini, GPT). These models collaborate using shared memory and Active Hybrid GraphRAG to perform code review, building, and maintenance. Through the Neural Link interface, the cluster can inspect semantic runtime states and dynamically modify UI and data in real time. It autonomously manages the entire engineering lifecycle, including ideation, construction, cross-review, and self-healing loops. Ideal for developers who need an AI engineering team to maintain and improve their codebase.
Capabilities
- ▪Multi-model cluster collaboration
- ▪Real-time code review and build
- ▪Self-healing loop mechanism
- ▪Shared memory and GraphRAG
- ▪Neural Link interface
Use cases
Setup
npm install neo.mjs
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Neo.mjs supports models such as Claude, Gemini, and GPT.
Supports models like Claude, Gemini, and GPT.
How do I deploy Neo.mjs to my codebase?
Configure it to point to your code repository and start the service.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.