Generate a map of your codebase to help AI agents understand your architecture, coding conventions, and patterns.
codebase-context is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view PatrickSys/codebase-context --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
This tool creates a map of your codebase that shows AI agents how your team builds software. It finds the most important files, coding patterns, and conventions so AI can write code that fits your project. It works locally on your machine and keeps your code private.
codebase-context is a local-first MCP server that helps AI coding agents understand your codebase before they start writing code. It generates a bounded conventions map that shows architecture layers, active patterns, golden files, and pattern drift. The tool uses AST-backed hybrid search to find the right local examples, with each result including pattern signals, file relationships, and quality indicators. It detects conventions from your code and git history, distinguishing what is common from what is rising or declining. Features include preflight checks for edit readiness, team memory support, and semantic search. It supports multiple frameworks (Angular, React, Next.js) and runs in stdio or HTTP mode. Your code never leaves your machine by default.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 77 days ago.
45 GitHub stars indicate community interest.
6 open issues signal maintenance load.
NOASSERTION license detected.
Help AI agents understand your team's coding conventions before generating code
Find the best example files in a large codebase for a given pattern
Detect which coding patterns are rising or declining in your project
Perform semantic search across your codebase with reranking for relevance
Provide preflight impact analysis before AI agents make edits
The tool runs locally and does not send code to external servers by default, but if you configure HTTP mode or custom embeddings, ensure data does not leave your environment.
As with any tool that analyzes code, there is a risk of exposing sensitive information if the output is shared with third parties.
45
Stars
12
Forks
6
Issues
NOASSERTION
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
Generate a map of your codebase to help AI agents understand your architecture, coding conventions, and patterns.
AI-assisted developers using Claude Code, Cursor, or GitHub Copilot, Engineering teams wanting consistent AI-generated code that follows team conventions, Tech leads managing large codebases with multiple patterns and frameworks
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The tool runs locally and does not send code to external servers by default, but if you configure HTTP mode or custom embeddings, ensure data does not leave your environment. As with any tool that analyzes code, there is a risk of exposing sensitive information if the output is shared with third parties.
Similar or complementary options to evaluate include roam-code, code-memory, MCP Server Collection.
Jun 6, 2026
2 security/trust notes recorded.
Setup difficulty is 2/5.