中/EN
Resources
Resources

Graphify: An AI Coding Skill That Turns an Entire Project into a Queryable Knowledge Graph

GitHub weekly #3 (90.8k stars, YC S26). /graphify maps code/docs/PDFs/images into a knowledge graph, tree-sitter AST local parsing (no LLM), each edge tagged EXTRACTED/INFERRED, not a vector index, traversable queries.

Published July 25, 20263 min read
<!-- graphify-resource | resource | Graphify Code Knowledge Graph -->

What Is Graphify: Turn an Entire Project into a Queryable Knowledge Graph

Graphify is an AI coding assistant skill-type /graphify in Claude Code / Codex / OpenCode / Cursor / Gemini CLI, and it maps your entire project (code, docs, PDFs, images, videos) into a knowledge graph you can query instead of grepping files. GitHub weekly rank #3, 90.8k stars, +8,498 weekly, YC S26.

Core Mechanism

  • Code parsed locally, no LLM: code is parsed with tree-sitter AST-deterministic, no LLM, nothing leaves your machine. (Docs, PDFs, images, video use your assistant's model or a configured API key for a semantic pass.)
  • Every edge explained: each connection is tagged EXTRACTED (explicit in source) or INFERRED (resolved by graphify), so you can tell what was read directly from what was inferred.
  • Not a vector index: no embeddings, no vector store-a real graph you traverse. Ask a question, trace the path between two things, or explain one concept.

How to Use (30-second start)

bash
uv tool install graphifyy      # install the CLI (or: pipx install graphifyy)
graphify install               # register the skill with your AI assistant

Then in your AI assistant:

text
/graphify .

You get three files:

text
graphify-out/
├── graph.html       open in any browser - click nodes, filter, search
├── GRAPH_REPORT.md  the highlights: key concepts, surprising connections, suggested questions
└── graph.json       the full graph - query it anytime without re-reading your files

Who It's For

  • Taking over a large codebase: new to a project, run /graphify first, read the graph and GRAPH_REPORT-10x faster than grinding through code.
  • Cross-language/cross-module tracing: trace a function call chain, the graph shows the path directly, no grep across files.
  • Code review/architecture understanding: read community detection (color blocks in the graph), understand module boundaries and coupling.

RAG is "find relevant fragments," graphify is "understand structure." RAG suits "where is this code written," graphify suits "which modules relate to this concept and how do they connect." They don't conflict-can be stacked.

Repo: https://github.com/safishamsi/graphify

Related