code-review-graph is a local-first code intelligence tool that builds a persistent structural map of a repository using Tree-sitter and SQLite.
It serves precise, context-aware code slices to AI coding assistants via the Model Context Protocol (MCP), significantly reducing token consumption during reviews.
- 01
Blast-radius analysis for impact tracking
- 02
Incremental graph updates via file-hash deduplication
- 03
Broad language support (56+ extensions) including Python, TS, Go, and Rust
- 04
GitHub Action for sticky, risk-scored PR review comments
- 05
Local-first SQLite storage with no external data transmission
Open Source
The tool is open-source and free to use under the MIT license.
Best for
Large repositories, monorepos, or multilingual projects where developers frequently review cross-file and cross-module modifications.
Not ideal for
Small projects with few files, trivial single-file diffs, one-off tasks, or teams not prepared to maintain index freshness.
An essential tool for power users of AI coding assistants who need to manage large-scale codebase context efficiently without sacrificing privacy or incurring excessive token costs.
As of July 2026, the latest version is v2.3.7, which includes refined MCP tool surfaces, improved token savings estimation, and enhanced multi-repo daemon capabilities.
As of
Is code-review-graph free?+
Yes - code-review-graph is Open Source. The tool is open-source and free to use under the MIT license.
Is code-review-graph open source?+
Yes - code-review-graph is open source. The tool is open-source and free to use under the MIT license.
Who is code-review-graph best for?+
Large repositories, monorepos, or multilingual projects where developers frequently review cross-file and cross-module modifications.
Who is code-review-graph not ideal for?+
Small projects with few files, trivial single-file diffs, one-off tasks, or teams not prepared to maintain index freshness.
What are the best code-review-graph alternatives?+
The closest code-review-graph alternatives on ai.dosa.dev are Greptile, Fern, remio - all listed under AI Codebase Knowledge & Generation.
Who makes code-review-graph?+
code-review-graph is developed by Tirth Kanani. It is listed in the AI Codebase Knowledge & Generation category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.