Neo
A self-improving code reasoning engine that learns from experience using persistent semantic memory. Neo uses multi-agent reasoning to analyze code, generate solutions, and continuously improve through feedback loops.
- Fact-Based Memory: Learns from every solution attempt using a scoped, supersession-based fact store
- Semantic Retrieval: Vector search finds relevant facts via Jina Code embeddings
- Code-First Generation: No diff parsing failures
- Local Storage: Privacy-first JSON storage in ~/.neo/facts/ directory
- Model-Agnostic: Works with any LM provider
- Three integration surfaces — each on equal footing:
- Run as an Agent (CAR / A2A) — host Neo as an Agent2Agent v1.0 endpoint other agents (or orchestrators) can call directly. Real inference path, not a CLI wrapper.
- Claude Code Plugin — six slash commands + a specialized agent inside Anthropic's Claude Code CLI.
- Codex Plugin — same six skills, packaged for OpenAI Codex CLI.
Why Neo? Why Care?
If you've been Vibe Coding, then Vibe Planning, then Context Engineering, and on and on, you have likely hit walls where the models are both powerful and limited, brilliant and incompetent, wise and ignorant, humble yet overconfident.
Worse, your speedy AI Code Assistant sometimes goes rogue and overwrites key code in a project, or writes redundant code even after just reading documentation and the source code, or violates your project's patterns and design philosophy.... It can be infuriating. Why doesn't the model remember? Why doesn't it learn? Why can't it keep the context of the code patterns and tech stack? ... -> This is what Neo is designed to solve.
Neo is the missing context layer for AI Code Assistants. It learns from every solution attempt, using vector embeddings to retrieve relevant patterns for new problems. It then applies the learned patterns to generate solutions, and continuously improves through feedback loops.
Table of Contents
Design Philosophy
Fact-Based Learning: Neo builds a semantic memory of facts — constraints, architectural decisions, patterns, review learnings, decisions, known unknowns, and failures — using vector embeddings for retrieval.
Code-First Output: Instead of generating diffs that need parsing, Neo outputs executable code blocks directly, eliminating extraction failures.
Scoped Storage: Facts are scoped to global, organization, or project level, stored locally in ~/.neo/facts/ for privacy and offline access.
Model-Agnostic: Works with OpenAI, Anthropic, Google, local models, or Ollama via a simple adapter interface.
How It Works
