Radar check
What we found when we opened it. Every bar is one fact, with its date.
Last code pushed 26 Oct 2026, the same day before this check.
Latest release v0.3.13 on 25 Oct 2026.
Public since June 2025, a little over 1 year.
5,284 stars and 704 forks.
6,653 commits and 1070 new issues in the last 90 days.
74 contributors. 1114 pull requests merged in 90 days.
A security policy says how to report a problem. 5 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
This tool reads your code files and builds a local map of how every function and class connects. It uses an embedded database that needs no server setup. You can ask questions in plain English or let an AI editor change your code safely. It supports many programming languages in one unified view. The software is free and open source under the MIT licence.
What it is
A command-line tool and Python library that parses source code with Tree-sitter and stores the structural relationships in an embedded SQLite graph database. It also acts as a Model Context Protocol server so coding agents can inspect the codebase directly.
What it is good for
Solo builders working on large or multi-language projects who want AI coding assistants to understand the entire architecture instead of guessing from a few open files.
- Builds a complete structural map of mixed-language codebases without needing a separate database server.
- Integrates directly with coding assistants through the Model Context Protocol.
- Performs surgical code edits using Abstract Syntax Tree patching with a preview before saving.
- Requires Python 3.12 or newer and ripgrep installed on your system.
- Initial repository parsing and graph building takes time and CPU resources on large monorepos.
- Managing graph updates as code changes adds an extra maintenance step to your workflow.
manual code searching with grep and naive file-chunking RAG systems
Claude Code
- Aider-AI/aider50k stars
Aider is a popular command-line AI coding assistant, whereas Code-Graph-RAG provides the structural knowledge graph backend for codebases.
- 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.
uv tool install "code-graph-rag[treesitter-full,ast-grep,semantic]"