JordanCoin/codemap

a project brain for your AI. Give LLMs instant architectural context without burning tokens

What it solves

Coding agents often struggle to understand the structural relationships in a codebase, as they typically only see the text of individual files. They cannot easily determine which files depend on a specific file, what the "blast radius" of a change is, or how complex build-system rules (like go.mod or tsconfig aliases) affect imports. codemap provides a structural "ground truth" that allows agents to understand dependencies and project orientation without expensive manual scanning.

How it works

codemap analyzes repositories using ecosystem-specific rules rather than simple string matching. It integrates with build tools like cargo metadata for Rust, go.mod for Go, and package.json for JS/TS to resolve imports accurately. It uses ast-grep for general import extraction across 21 languages. To ensure reliability, it implements a "coverage contract," explicitly reporting when it cannot resolve a dependency so that agents don't mistake a partial graph for a complete one.

Who it’s for

It is designed for developers using AI coding agents (such as Claude Code or Codex) who need their agents to have a deeper, structural understanding of their project's architecture and dependency flow.

Highlights

  • Build-System Aware Resolution: Resolves imports using real ecosystem rules for Go, Rust, JS/TS, and Dart/Flutter.
  • Blast Radius Analysis: Quickly identifies "hub files" (highly imported files) and determines exactly who will be affected by a change.
  • Agent Integrations: Provides an MCP server with 19 tools, session hooks for automatic context, and a context protocol for machine-readable project intelligence.
  • Cross-Agent Handoff: Tracks which files were edited by which agent, allowing for seamless continuation when switching between different AI tools.
  • Remote Analysis: Ability to analyze public GitHub or GitLab repositories without requiring a full local clone.

Related

  • Project
    DeusData/codebase-memory-mcp

    A high-performance code intelligence engine that builds a structural knowledge graph of codebases to provide AI agents with efficient, low-token access to architectural insights.

  • Project
    harshkedia177/axon

    A codebase knowledge graph tool that indexes structural dependencies and exposes them via a visual dashboard and MCP tools for AI agents.

  • Project
    justrach/codedb

    codedb is a zero‑dependency, Zig‑based server that builds rich indexes (trigram, word, symbol, call‑graph) of a local codebase and exposes them via the Model Context Protocol (JSON‑RPC over stdio). AI coding assistants (Claude Code, Cursor, Gemini CLI, etc.) can query for file trees, outlines, symbol definitions, callers, and full‑text search in sub‑millisecond latency, dramatically reducing token usage. It runs as an MCP daemon (`codedb mcp`) or an HTTP server, updates incrementally via a file watcher, and ships signed binaries for macOS, Linux, and Windows.

  • Project
    tirth8205/code-review-graph

    A local code knowledge graph that provides AI coding tools with precise review context via MCP, reducing token consumption by identifying the blast radius of changes.

  • Project
    CodeGraphContext/CodeGraphContext

    A toolkit and MCP server that indexes local code repositories into a graph database to provide AI agents and developers with structural context like call chains and class hierarchies.