CodeGraph
Local-first code intelligence tool for AI coding agents
Visit colbymchenry.github.io ↗What is CodeGraph?
CodeGraph parses codebases into queryable knowledge graphs that AI agents can understand efficiently. It uses Tree-sitter for fast, incremental parsing across 20+ languages, extracting accurate symbols and relationships from real abstract syntax trees. The tool exposes this graph via MCP (Model Context Protocol) to Claude Code, Cursor, Codex, and other AI agents, enabling them to answer questions with fewer tool calls.
Designed for developers working with AI coding assistants, CodeGraph runs entirely local-first with no compilation needed. It supports impact analysis to trace callers, callees, and the full scope of changes before modifying code, and includes framework-aware parsing for routes and cross-platform bridging.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered CodeGraph automatically. Evidence: GitHub colbymchenry/codegraph; repo has .claude, .cursor, AGENTS.md. View source.
Similar vibe-coded apps
Open-source control plane for orchestrating multiple AI coding agents
Open-source AI job search agent that runs locally in your CLI
IDE to orchestrate multiple coding agents in one workspace
AI-native engineering philosophy and plugin for coding agents
Open-source runtime layer that turns LLMs into working agents
AI framework that injects project specs into coding agents across 20+ platforms
