# tirth8205/code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

Repository: https://github.com/tirth8205/code-review-graph
Canonical: https://ross.abutalabs.com/products/code-review-graph
Homepage: https://code-review-graph.com
Language: Python
License: MIT
License Family: permissive
Topics: ai-coding, claude, claude-code, code-review, graphrag, incremental, knowledge-graph, llm, mcp, python, static-analysis, tree-sitter
Last push: 2026-08-26T13:06:29+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 13
- inputs: {"age_days": 188, "days_push": 7, "days_rel": 12, "gap_med": 1.5, "n_releases_24m": 29}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 30891, forks 2809 (observed 2026-08-28T04:11:56.508020+00:00)

## What it is
A local-first code intelligence tool that builds a persistent knowledge graph of a codebase using Tree-sitter static analysis, exposed via MCP and a CLI. It lets AI coding assistants retrieve only relevant code context, reducing token usage in code review and large-repo workflows.

## Use cases
- reduce token usage when AI tools review my code
- give Claude Code precise context from a large repo
- build a persistent code knowledge graph locally
- index my codebase incrementally for AI assistants
- serve code context to AI tools over MCP
- static analysis map of functions and dependencies for LLMs

## When to choose
- you use MCP-compatible AI coding tools (e.g. Claude Code) on large repositories
- you want local-first, private code indexing without sending code to a cloud service
- you need token-efficient code review or context retrieval

## When to avoid
- you need deep semantic or runtime analysis rather than structural parsing
- your project is small enough that full-file context is cheap
- you need an IDE-native indexing solution instead of MCP/CLI

## Facets
- artifact type: cli-tool
- maturity: active
- function: mcp, parser, linter, search-engine, cli, developer-tools
- domain: developer-tools, large-language-models, version-control, apis
- platform: python, cli, cross-platform
- tags: code-review, knowledge-graph, tree-sitter, token-efficiency, ai-coding, local-first, graphrag, incremental-indexing, ai-agents

## Member repositories
- tirth8205/code-review-graph (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:56.508020+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 2026-08-29T16:52:36.003360+00:00, confidence not recorded.
  - readme: https://github.com/tirth8205/code-review-graph (fetched 2026-08-28T04:11:56.508020+00:00, sha e1a69f06afa3)
  - homepage: https://code-review-graph.com (fetched 2026-08-29T07:49:31.785224+00:00, sha 150ac491b3c4)
  - registry_pypi: https://pypi.org/pypi/code-review-graph/json (fetched 2026-08-29T07:49:31.794706+00:00, sha a62be0cafdab)
- Data as of 2026-08-30T08:39:29.467469+00:00.