[GitHub Trending] colbymchenry/codegraph
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Code knowledge graph reducing tokens for AI agents is novel, actionable, and perfectly matches the reader's interests.
CodeGraph, an open-source tool providing semantic code intelligence, pre-indexes codebases into a knowledge graph of symbol relationships and call graphs, enabling AI coding agents like Claude Code and Cursor to query the index via an MCP server instead of scanning files with grep/glob. Benchmarks across 7 real-world codebases (including VS Code, Django, Tokio) using Claude Opus 4.7 show average reductions of 35% in cost, 59% in tokens, 49% in time, and 70% in tool calls, with gains scaling on larger repos. The tool installs with a single curl command, bundles its own runtime, and auto-configures supported agents.
Install CodeGraph on your project with a single curl command and run `codegraph init -i` to cut agent costs and tool calls by more than a third.
For engineers using AI coding agents on large codebases, CodeGraph drastically reduces token consumption and latency by replacing file-scanning with a local, pre-built knowledge graph, directly improving agent efficiency and lowering costs.
CodeGraph Supercharge Claude Code, Cursor, Codex, OpenCode, and Hermes Agent with Semantic Code Intelligence ~35% cheaper · ~70% fewer tool calls · 100% local Get Started No Node.js required — one command grabs the right build for your OS: # macOS / Linux curl -fsSL https://raw.githubusercontent.com/colbymchenry/codegraph/main/install.sh | sh # Windows (PowerShell) irm https://raw.githubusercontent.com/colbymchenry/codegraph/main/install.ps1 | iex Already have Node? Use npm instead (works on any version): npx @colbymchenry/codegraph