BigHugger
GH Repository · Graphify-Labs

graphify

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

stars
118,764
30-day movement
+331110/day
Related entries
60
Connections
2
python/uvPythonpythonllmdeveloper-toolscode-analysisclaude-codecursorknowledge-graphgeminileidenragcodexdockerai-agentsopenclawcode-searchgraphragskillsantigravitytree-sittermcpast

Graphify turns a codebase, including docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. It ships as a /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI, using local deterministic AST parsing (tree-sitter) with explained edges and no vector store.

Reach for it when you want structured, explainable code search and retrieval over a repository instead of embedding-based RAG.

Use it to

  • Index a codebase into a queryable knowledge graph
  • Search code and docs via graph-based RAG
  • Run community detection (Leiden) over code relationships
  • Expose the graph through MCP to coding agents
  • Explain every edge in the generated graph

For Developers using AI coding agents on large codebases

Role
rag
Language
Python
Licence
Apache-2.0
Forks
11,489
Open issues
633
Last push
2026-09-16
Latest release
v1.0.0 · 2026-04-05
topicsknowledge-graphgraphragastcode-analysisai-agentsrag