neo-agent-brain
Active·★ 11·MIT·Updated 2026-10-22
Neo-agent-brain serves as the 'Brain' of the Neo.mjs AI engineering team, functioning as an Agent OS. It provides persistent identity, shared institutional memory, repository knowledge, and durable coordination for a swarm of AI maintainers from diverse model families, enabling robust cross-family review and self-evolving workflows.
#Multi-Agent System#Agent OS#Institutional Memory#Knowledge Base#AI Orchestration#GitHub Automation#Self-Evolution
01
Features
01Durable, provenance-aware reasoning across agents and sessions via Memory Core + Native Edge Graph.
02Semantic understanding of source code, guides, issues, and pull requests with a Knowledge Base.
03Durable peer coordination and wake substrate (A2A) for named maintainers and harnesses.
04GitHub-native engineering lifecycle operations (issues, PRs, reviews).
05Self-evolution and priority steering through REM digestion + Golden Path synthesis, driven by model friction.
02
Compatibility
Node.js
Runtime
Verified via docs
03
Quick start
1
$ git clone https://github.com/neomjs/neo-agent-brain.git
2
$ cd neo-agent-brain
3
$ npm install
04
Use cases
↳Building and maintaining a professional, end-to-end AI engineering team with diverse AI models.
↳Enabling multi-agent collaboration with shared institutional memory and cross-family review disciplines.
↳Automating GitHub-native workflows for issue tracking, pull request management, and code reviews by AI agents.
↳Operating agent institutions that evolve and improve their capabilities based on real-world friction (MX loop).
05
Alternatives
forge-orchestrator★ 162
NXTG-Forge orchestrator: multi-AI task orchestration with file locking, knowledge capture and drift detection. Rust. Public preview (source-available, FSL-1.1-ALv2).
claude-vibe-squad★ 164
Multi-model AI orchestration where behaviour is Markdown, not code. One coordinator routes scoped task packets to 71 role-based specialists across 5 model families (Codex / Claude / Gemini / Grok / Kimi) — each working in an isolated git worktree, each reviewed by a rival family before it lands. One tmux session, no server.
ruflo★ 78.4k
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration
musubi★ 11
Musubi (結び) — Ai Agent shared memory and thought layer. The braiding of threads between presences.
MassGen★ 1.1k
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai
Comments
Log in to leave a comment
No comments yet. Be the first!