colbymchenry/codegraph
CodeGraph is an open-source semantic code intelligence tool that builds a pre-indexed knowledge graph of codebases. Powered by a Rust kernel, its README describes local operation and automatic synchronization when files change. The utility exposes a Model Context Protocol server that supplies coding assistants with precise structural context across files, designed to reduce repeated file reads.
Targeted at software engineers and engineering teams working with AI agents like Claude Code, Cursor, Codex CLI, OpenCode, Hermes Agent, Gemini, and GitHub Copilot, it bridges project structure directly into agent environments. Supported languages include TypeScript, JavaScript, Python, Go, Rust, Java, C#, PHP, Ruby, C, C++, Swift, Kotlin, and others.
Pre-built bundles require no Node.js runtime. macOS and Linux users install via curl -fsSL https://raw.githubusercontent.com/colbymchenry/codegraph/main/install.sh | sh, while Windows users run irm https://raw.githubusercontent.com/colbymchenry/codegraph/main/install.ps1 | iex in PowerShell. Systems with Node.js can use npm i -g @colbymchenry/codegraph. Setting up involves running codegraph install to configure agent MCP endpoints, followed by codegraph init inside project folders.
The GitHub snapshot shows the repository is not archived and records an MIT license. For another code-graph tool, compare Graphify; its workflow and scope are different.
Data as of : 76286 stars · 5069 forks.