Knowledge Graph

Knowledge Graph for Claude Code and Codex

Persistent, git-native memory that makes your AI coding agent actually remember. Zero databases, zero services — just bash, jq, and your own commits.

Claude Code and other AI coding agents forget everything between sessions — you end up re-explaining the same project context every time. Knowledge Graph fixes that by turning your file operations and git history into a lightweight, evidence-based memory layer that lives inside your repo.

First-class support for:

- Claude Code — auto-tracks reads and writes via hooks, injects a work snapshot on every session start, rebuilds context after /clear and /compact
- Codex / Cursor / Windsurf / any MCP client — 7 tools and 20+ resources exposed by the bundled MCP stdio server (kg_read_node, kg_query, kg_recent_work, kg_blind_spots, …)

No embeddings. No vector stores. No external services. Works on macOS, Linux, and Windows.

Who this is for

- Vibecoders — you describe intent, the agent writes code. Knowledge Graph gives the agent the project context you never had to learn, so one-line requests turn into working changes instead of destructive rewrites. *From the maintainer (a vibecoder himself): goal completion and "actually what I wanted" rate jumped at least 10× after installing it — "10× is the floor."*
- Senior developers — you want structured, auditable context that your AI agent respects. Every rule traces back to a commit hash or a recorded error event. No hallucinated conventions.
- Teams — rules live in canonical CLAUDE.md nodes right next to the code they govern. Codex reads the same nodes through MCP, so teams avoid split-brain knowledge. Share via git push.

Quick Start

macOS / Linux / WSL

Windows (PowerShell + Git Bash)

Then:

1. Restart Claude Code so hooks activate,…