#11 · Primary category: AI Coding Assistants
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.
Project last updated:08/29/26
GitHub Stars
112.3K
Forks
10.9K
Contributors
235
License
Apache-2.0
Why we included this project
Graphify gives an AI coding assistant a queryable map of your project, so Claude Code, Cursor, Codex, or Gemini CLI can answer questions about classes, functions, imports, and call relationships without re-reading your files. The parsing runs locally with tree-sitter, producing deterministic AST structure with no LLM and no vector store, which means you're not spending tokens or sending source code off your machine. Each connection is labeled as extracted from the source or inferred by the tool, so you can see what the assistant is actually reasoning over. The explain, path, and query commands are handy for tracing how two components connect or figuring out what a concept depends on, which helps a lot when you're dropped into a large or unfamiliar codebase.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.