whereismyai
CodeGraph
CodeGraph is a pre-indexed code knowledge graph that auto-syncs on changes to give AI agents surgical context and reduce tool calls.
CodeGraph is a pre-indexed code knowledge graph tool that automatically syncs on code changes and provides surgical context for AI coding agents. It works by building a local graph of every symbol, call edge, and dependency in a codebase, allowing agents to query source code, call paths, and change impact in a single call instead of crawling files individually. It is designed for developers using AI agents like Claude Code, Cursor, Codex, OpenCode, Hermes Agent, Gemini, Antigravity, Kiro, and GitHub Copilot. The platform features Rust-powered extraction, automated background file watching, and multi-language structural analysis. It supports platforms including VS Code, JetBrains, and CLI environments, and operates 100% locally.
CodeGraph at a glance
- Best for: Software engineer
- Runs on: CLI, VS Code, JetBrains, self-hosted
- Pricing: Free
- Released: January 2026
- Category: AI coding tool
- Website: github.com/colbymchenry/codegraph
Key features
- Pre-indexed knowledge graph
- Auto-syncs on file changes
- Rust-powered graph extraction
- Cross-file dependency resolution
- Framework-aware route mapping
- Local .codegraph directory storage
- Multi-agent CLI configuration installer
Use it for
- Answering architectural questions with AI agents
- Analyzing the blast radius of code changes
- Tracing complex call paths and dependencies
- Reducing token usage and tool calls during AI sessions
Companions
Tools that articles about CodeGraph recommend using with it, each with its job.
- Claude Code — Installs as a skill so the agent queries the graph before grepping.
- Codex — The installer wires the same graph into Codex.
- Obsidian — Open the output as a vault to see how the code clusters.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
Alternatives to CodeGraph
- Graphify — It replaces grepping with traceable graph paths, reducing token usage significantly.
- CodeSight — Reduces AI token usage significantly and maps projects instantly.
- Code Review Graph — Provides a median 63x context reduction while keeping all code processing local.
- Cody — Provides complete codebase context for developers and AI agents at scale.
- Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
- CodePilot — Consolidates multiple AI agents and local model connections in one workspace.
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- Rubi — It cuts AI token waste by keeping sessions short and mapping project knowledge.
- Dosu — It enables a shared knowledge cache so agents avoid redundant data gathering.
- GoCodeo — Generates production-ready code, explains code, and creates tests in seconds.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- Stoneforge — Runs isolated git worktrees and automated merges to prevent conflicts.
All CodeGraph alternatives