[GitHub Trending] colbymchenry/codegraph
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Code knowledge graph to optimize AI coding agents, directly applicable and trending.
CodeGraph (colbymchenry/codegraph) generates a local, pre-indexed knowledge graph of symbol relationships and call graphs for AI coding agents like Claude Code, Cursor, and OpenCode. In benchmarks across 6 codebases (VS Code, Excalidraw, Claude Code, Alamofire, Swift Compiler), agents using CodeGraph averaged 92% fewer tool calls and 71% faster exploration, with zero file reads — including on a 25,874-file Swift Compiler codebase. The tool supports cross-language queries (e.g., Python+Rust in Claude Code) and uses FTS5 for full-text search.
Integrate CodeGraph into your AI-assisted development workflow to slash tool call costs and exploration latency, especially on large monorepos.
For a solutions architect focused on developer experience and AI agent orchestration, CodeGraph directly tackles the token-cost and latency inefficiency of agent-based code exploration by offloading context-building to a static analysis graph.
CodeGraph Supercharge Claude Code, Cursor, Codex, and OpenCode with Semantic Code Intelligence 94% fewer tool calls · 77% faster exploration · 100% local Get Started npx @colbymchenry/codegraph Interactive installer auto-configures your agent(s) — Claude Code, Cursor, Codex CLI, opencode Initialize Projects cd your-project codegraph init -i Why CodeGraph? When Claude Code explores a codebase, it spawns Explore agents that scan files with grep, glob, and Read — consuming tokens on every tool call. CodeGraph gives those agents a pre-indexed knowledge graph