• Picks
  • Discover
  • Alternatives
  • About

© 2026 Willet

  • Newsletter
  • About
  • FAQ
  • Terms
  • Privacy & Cookies
Join the Discord (opens in a new tab)
Colby Mchenry avatar

CodeGraph

Local code graph that gives AI coding agents structural context via MCP

  • AI coding agents
  • Developer tools
View on GitHub
Website

What it is

CodeGraph parses a project into a graph of symbols, calls, and cross-file references, stores it in a local .codegraph directory, and keeps it updated as files change. It exposes the graph through an MCP server and CLI so agents such as Claude Code, Cursor, Codex, and Copilot can look up relevant code with fewer searches and tokens. Developers who lean on coding agents install it once, wire it to their agents with one command, and index each repository locally.

Images

Facts

Stars
74,520 GitHub stars.
74,520

Forks
4,822
Commits
1,535
Contributors
49
Language
C
License
MIT
Last commit
Oct 20, 2026
On GitHub since
January 2026
First release
May 2026
Platforms
macOS, Windows, Linux, CLI, library
Self-hostable
No
Author
Colby Mchenry
Tags
  • coding-agent
  • mcp-server
  • context-engineering
  • knowledge-graph
  • code-intelligence

Last synced from GitHub on Oct 20, 2026

The 10 best overlooked open-source projects, every Monday.

Share and more

Comments

No comments yet. Start the conversation.

Similar projects

  • Martin Vogel avatar

    codebase-memory-mcp

    Local MCP server that indexes code into a queryable knowledge graph

    47k
  • Tirth Kanani avatar

    code-review-graph

    Local code graph that feeds AI coding assistants only the relevant files

    32.3k
  • Graphify Labs avatar

    Graphify

    Codebase-to-knowledge-graph skill for AI coding assistants

    130k
  • Vitali Avagyan avatar

    Code-Graph-RAG

    Maps a codebase into a knowledge graph to query and edit in plain English

    5.3k