Back to directory

CodeGraph

CodeGraph is a locally indexed, auto-syncing code knowledge graph that gives coding agents such as Claude Code, Cursor and Copilot structural context with fewer tokens and fewer tool calls than repeated file reads.

CodeGraph

A single installer downloads a self-contained CLI with no Node.js requirement, a separate step wires the CodeGraph MCP server into whichever detected agents the user picks, such as Claude Code, Cursor, Codex CLI, OpenCode, Gemini CLI, Antigravity, Kiro and GitHub Copilot, and a per-project init command builds the initial graph. After that, a background watcher keeps the graph updated automatically as files change, so it should never go stale.

All indexing and querying happen on the user's machine, and an uninstall command removes every agent configuration and CLI install it finds, showing what will be deleted first. A separate hosted platform, still in early access, is planned to analyze pull requests for affected flows and business-logic risk.

The core engine is written in Rust. C, MIT licensed.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.