CodeGraph turns codebases into Neo4j graphs so agents can do dependency-aware refactoring
JeremyCMorgan · x · 2026-11-11
CodeGraph Analyzer is an open-source static analysis engine that parses multi-language codebases into an AST-based Neo4j graph database and exposes it to AI agents via MCP (Model Context Protocol).
Key points
- Supports TypeScript/JavaScript, Python, and more, building a queryable "digital twin" of your software ecosystem
- The most interesting use case is dependency-aware refactoring: letting an agent trace which services, functions, and APIs are affected before changing code
- Ships with a Neo4j launch script and Python parser for easy setup
The repo has 89 stars on GitHub and is worth a try for developers who want coding agents to actually understand large, multi-language codebases.
More from coding & agent
- 30 Shopify engineers rebuilt a 300-screen app in 12 weeks with agents writing most of the code — schwentker · 2026-11-11
- Hugging Face adds decision pipeline: models output option probabilities without generating text — kalyan_kpl · 2026-11-11
- Anthropic says Claude ported itself to AMD GPUs in 3 days, writing ~100% of kernels unassisted — AccBalanced · 2026-11-11
- Dev tests Fable 5.2 + Unreal Engine to recreate golden-age competitive shooters — FanaHOVA · 2026-11-11
- Fable 5.2 builds a 3D game in 76 min for ~$42 in tokens, roughly matching Opus 5.5 — FinanceYF5 · 2026-11-11
- Procedural 3D dragon in threejs generated as pure code, demo online — majidmanzarpour · 2026-11-11