Radar check
What we found when we opened it. Every bar is one fact, with its date.
Last code pushed 16 Oct 2026, 9 days before this check.
Latest release v2.3.9 on 18 Sep 2026.
Public since February 2026, 8 months.
32,387 stars and 2,957 forks.
427 commits and 118 new issues in the last 90 days.
143 contributors. 109 pull requests merged in 90 days.
A security policy says how to report a problem. No published security advisories.
How the bars are scored
- Alive. Days since the last code push: a week or less 100, a month 90, three months 70, six months 50, a year 30, eighteen months 15, older 0.
- Releases. Age of the latest GitHub release, on a similar scale; no bar when the project publishes no releases.
- Maturity. Age of the project: eight years 100, five 90, three 70, two 55, one 40, six months 25, younger 10.
- Adoption. Stars on a log scale: 100,000 stars is 100, 10,000 is 80, 1,000 is 60, 100 is 40.
- Activity. Commits in the last 90 days: 300 or more 100, 100 85, 30 65, 10 45, any 25.
- Community. People who have contributed: 100 or more 100, 30 80, 10 60, 5 40, 2 25, one 10.
- Security. A published security policy 80, none 40; published advisories are listed, not scored.
Checked by Repo Radar on 26 Oct 2026 from the repository on GitHub.
In simple English
AI coding tools often read your entire project to answer a question. This wastes time and money. This tool builds a local map of your files, functions, and imports in a single database. When you ask an AI assistant for help, it reads only the parts of the code that your changes actually touch. It runs entirely on your own computer and does not send your code to the cloud.
What it is
A local code knowledge graph that parses source files with Tree-sitter (a parser generator that builds a concrete syntax tree for source code files) and serves compact review context over the Model Context Protocol (an open standard for connecting AI models to data sources and tools). It updates incrementally as you edit your code and works with many popular AI coding assistants.
What it is good for
Solo builders who use AI coding assistants on large projects and want to stop wasting money on token limits and slow reviews.
- Reduces the number of tokens sent to your AI assistant by dozens of times.
- Updates only the files that changed since your last edit, keeping the graph fast.
- Integrates directly with your existing AI coding tools through automated configuration commands.
- Requires Python 3.10 or newer installed on your system.
- Initial build takes up to a minute on large repositories.
- Requires a supported AI coding assistant or editor to make full use of the generated context.
manually copying and pasting whole code files into AI chat prompts
Claude Code
- Aider-AI/aider50k stars
A command-line AI coding assistant that edits code in git repositories, but manages context per session rather than building a persistent knowledge graph.
- basicmachines-co/basic-memory4.3k stars
Gives an AI assistant a memory that is stored as plain text files you can read.
- deepset-ai/haystack27k stars
A Python framework for joining language models, document search and tools into one working pipeline.
- Giskard-AI/giskard-oss5.9k stars
A Python library that writes tests for language-model programs and tries to break them on purpose.
pip install code-review-graph code-review-graph install code-review-graph build