#369 · Primary category： AI Agents & Automation
neo
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.
Project last updated：08/30/26
GitHub Stars
3.3K
Forks
232
Contributors
89
License
MIT
Why we included this project
Neo.mjs is one of the more unusual AI projects around because it treats a live application as the place where agents actually do their work. Rather than running a single model on its own, it spins up a swarm of agents from rival labs (Claude, Gemini, GPT) that share reasoning through a persistent memory core and a graph-retrieval layer, and those agents can inspect and modify real UI and data while the app is running. That makes it both a practical study in multi-model collaboration with durable long-term memory and a working frontend runtime for teams exploring persistent agent memory, MCP-based tooling, or agentic software engineering. Just go in expecting a heavy, opinionated platform with a steep learning curve, not a small drop-in library.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.