# colbymchenry/codegraph

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

Repository: https://github.com/colbymchenry/codegraph
Canonical: https://ross.abutalabs.com/products/codegraph
Homepage: https://colbymchenry.github.io/codegraph/
Language: C
License: MIT
License Family: permissive
Last push: 2026-08-26T17:09:09+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 16
- inputs: {"age_days": 227, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 68252, forks 4341 (observed 2026-08-28T04:12:20.872554+00:00)

## What it is
CodeGraph is a local-first tool that indexes any codebase into a queryable knowledge graph using Tree-sitter parsing, exposing it to AI coding agents via an MCP server. It auto-syncs on code changes and supports Claude Code, Cursor, Codex, Gemini, and other agents, reducing token usage and tool calls.

## Use cases
- index my codebase as a knowledge graph for AI coding agents
- reduce token usage when Claude Code explores a large repo
- trace callers and impact of a symbol before refactoring
- give Cursor or Codex semantic code context via MCP
- auto-sync code index when files change
- answer codebase questions in fewer agent tool calls

## When to choose
- you use AI coding agents (Claude Code, Cursor, Codex, etc.) on medium-to-large codebases
- you want fully local, private code indexing with no cloud dependency
- you need fast impact analysis and symbol relationship queries
- you want to cut agent token costs and tool-call round trips

## When to avoid
- your project is tiny and agents navigate it fine without indexing
- you need a hosted/team-shared code intelligence platform (still on waitlist)
- your language is outside the 20+ Tree-sitter supported languages
- you need deep semantic analysis beyond AST-derived symbols and edges

## Facets
- artifact type: cli-tool
- maturity: active
- function: search-engine, parser, mcp, developer-tools, documentation
- domain: developer-tools, programming-languages, artificial-intelligence
- platform: windows, cli
- tags: code-knowledge-graph, mcp-server, ai-coding-agents, tree-sitter, impact-analysis, local-first, code-intelligence, ai-agents, linux, macos, nodejs

## Member repositories
- colbymchenry/codegraph (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:20.872554+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:16:23.773138+00:00, confidence not recorded.
  - readme: https://github.com/colbymchenry/codegraph (fetched 2026-08-28T04:12:20.872554+00:00, sha 0ecb0b77e16a)
  - homepage: https://colbymchenry.github.io/codegraph/ (fetched 2026-08-28T17:51:56.067848+00:00, sha 9adca639e23d)
- Data as of 2026-08-30T08:39:29.467469+00:00.