code-review-graph
Pilot it+3.8k this week★ 30,937 · 2,815 forks
Local code intelligence graph for AI coding tools
Worth a timeboxed spike before you bet on it.
Who it's for
Small teams with large codebases and AI tooling
What it replaces
Manual code review and mapping processes
The catch
Steep learning curve and potential performance overhead
Your first hour
Clone the repository and run the demo script locally
The numbers
Stars30,937
Forks2,815
Stars added (7d)+3.8k
Open issues116
LanguagePython
LicenceMIT
Last pushUpdated today
Project age6 months old
Maintainers describe it as: “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.”
ai-codingclaudeclaude-codecode-reviewgraphragincrementalknowledge-graphllmmcppython
code-review-graph, in short
- Should a small team use code-review-graph?
- Pilot it. Worth a timeboxed spike before you bet on it. Small teams with large codebases and AI tooling
- What does code-review-graph actually do?
- Local code intelligence graph for AI coding tools
- What does code-review-graph replace?
- Manual code review and mapping processes
- What is the downside of code-review-graph?
- Steep learning curve and potential performance overhead
- Can code-review-graph be used in a commercial product?
- Its licence is MIT, which is permissive and generally fine for commercial use. Confirm against the LICENSE file in the repository.