PatrickSys/codebase-context

Local-first Second brain for AI agents working on your codebase - detects your team coding conventions and patterns, brings in persistent memory, code-generation checks, and hybrid search with evidence scoring. Exposed through CLI and MCP server.

56
/ 100
Established

Tired of AI agents generating code that doesn't align with your team's existing conventions? This tool provides AI agents with deep context about your codebase, including coding patterns, architectural decisions, and even past workarounds. It takes your team's code and git history as input and helps AI agents produce code that seamlessly integrates, while also remembering past corrections and surfacing critical information before any edits are made. It's designed for software developers and engineering teams using AI code assistants.

Available on npm.

Use this if your AI agents struggle to generate code that fits your team's specific coding styles, architecture, and established patterns, or if they repeatedly make the same mistakes despite corrections.

Not ideal if you are looking for a simple code autocomplete tool or if your team does not use AI agents for code generation and refactoring.

software-development AI-assisted-coding code-quality developer-workflow code-maintenance
Maintenance 10 / 25
Adoption 7 / 25
Maturity 22 / 25
Community 17 / 25

How are scores calculated?

Stars

33

Forks

8

Language

TypeScript

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/PatrickSys/codebase-context"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.