{"id":"code-graph-rag","name":"Code Graph RAG","homepage":"https://github.com/vitali87/code-graph-rag","repo_url":"https://github.com/vitali87/code-graph-rag","category":"developer-tools","subcategories":["code-analysis","rag","knowledge-graph"],"tags":["rag","knowledge-graph","memgraph","tree-sitter","code-analysis","mcp","monorepo","multi-language","ast-parsing","code-search"],"what_it_does":"Graph-based RAG system that parses multi-language codebases using Tree-sitter, builds knowledge graphs in Memgraph, and enables natural language queries about code structure and relationships. Supports parsing 11+ languages, AI-powered Cypher query generation, surgical code editing with AST targeting, shell command execution, and real-time graph updates via file watching. Includes an MCP server for Claude Code integration.","use_cases":["Natural language querying of large monorepo codebases","Understanding code structure, function relationships, and call graphs","AI-assisted code navigation and exploration across multiple languages","Surgical code editing with AST-aware diff previews","Onboarding to unfamiliar codebases by querying architecture semantically"],"not_for":["Simple single-file code analysis (overkill)","Runtime performance profiling or debugging","Non-code document RAG (focused specifically on source code)"],"best_when":"You have a large multi-language codebase and want AI-powered structural understanding, natural language code search, and graph-based relationship analysis.","avoid_when":"You have a small codebase where grep/IDE search suffices, or you cannot run Docker (required for Memgraph).","alternatives":["Sourcegraph (hosted code intelligence)","Aider (AI pair programming without graph)","Continue.dev (IDE-based AI code assistant)","Codeium (AI code completion)"],"af_score":63.0,"security_score":55.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":"unknown","last_evaluated":"2026-03-01T09:50:05.415165+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":"Depends on chosen LLM provider","data_source":"llm_estimated","measured_on":null}}