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 v0.12.1 on 16 Oct 2026.
Public since February 2026, 8 months.
47,504 stars and 3,907 forks.
2,695 commits and 568 new issues in the last 90 days.
200 contributors. 666 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
This tool reads your source code, documentation and configuration files to build a map of how everything connects. When you ask an AI coding agent to fix a bug or add a feature, the agent uses this map to find the right files immediately. It runs entirely on your own computer without sending your data to any cloud service. It installs with a single command and works with popular coding assistants. You get faster answers and use fewer tokens without paying any subscription fees.
What it is
An MCP (Model Context Protocol, a way for AI tools to talk to local data sources) server written in C that parses codebases into a persistent SQLite knowledge graph. It includes a native backend with seventeen tools, automatic agent integrations, and an optional browser interface called CBM Lens.
What it is good for
Solo builders working with large codebases who want to stop their AI coding assistants from guessing blindly, reading unnecessary files, and losing track of how different services call each other.
- Runs entirely offline on your machine with no API keys or cloud service required.
- Includes an optional browser visualizer to explore code relationships in 3D or 2D maps.
- Reduces token consumption by feeding precise code context directly to your AI agent.
- Requires compiling or running native binaries which can trigger false positives on antivirus software.
- Consumes local disk space and memory to maintain the persistent SQLite knowledge graph.
- Setup requires restarting your coding agent and ensuring your client configuration matches.
Manual code exploration and slow grepping across large unfamiliar repositories
Claude Code, Cursor, or any MCP-compatible coding assistant
- Aider-AI/aider50k stars
A command-line coding assistant that edits local files with repository awareness.
- Kong/insomnia40k stars
A desktop application for sending requests to an interface and reading what comes back.
- microsoft/playwright-mcp39k stars
A server that lets an AI assistant drive a real browser, using the page's own structure rather than screenshots.
- Kilo-Org/kilocode28k stars
An open-source coding assistant for VS Code, JetBrains editors and the terminal, which can edit several files at once.
curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash codebase-memory-mcp daemon start --open --port=9749