code-graph-rag
Enables teams to navigate and modify large monorepos efficiently by combining semantic search with code structure awareness, reducing onboarding time and red…
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
- Ask Claude to find all functions calling a specific deprecated API across your entire codebase.
- Generate a dependency map showing how modules interact in your monorepo architecture.
- Ask Claude to explain the data flow between microservices by analyzing code relationships.
Enables teams to navigate and modify large monorepos efficiently by combining semantic search with code structure awareness, reducing onboarding time and reducing risk of cross-module breaks.
Engineering teams managing multi-language monorepos seeking faster code comprehension and safer refactoring workflows.
https://github.com/vitali87/code-graph-rag
By vitali87
How to Get It
claude plugins install vitali87/code-graph-rag
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Find all functions calling a specific deprecated API across my entire codebase
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Graph-Code: A Graph-Based RAG System for Python Codebases — Hacker News · 4 pts
- Monorepos solved: graph-based search — Hacker News · 3 pts
- Graph-Code: A Graph-Based RAG System for Any Codebases — Hacker News · 3 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 2,296 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 2,296 GitHub stars; contributors unknown; last commit 0d ago; license MIT.