100100 Ideas AI
Submit Tool

graphify

MCPOpen source

Turn any codebase into a queryable knowledge graph with local AST parsing, no vector store.

110kApache-2.0

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.

Pros

  • +Fully local and deterministic AST parsing, no data leaves your machine
  • +Every graph edge is explained as extracted or inferred
  • +Works with multiple AI coding assistants (Claude Code, Cursor, Codex, etc.)
  • +Generates interactive graph.html and queryable graph.json

Cons

  • −Semantic analysis of docs/PDFs requires an LLM or API key
  • −May have a learning curve for non-developers
  • −Graph size could become large for very big codebases

Target audience: Developers and engineering teams using AI coding assistants who want to understand and navigate complex codebases efficiently.

Related tools

Other open-source tools that share tags with graphify.

jcodemunch-mcp

MCPNOASSERTION

Token-efficient MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST parsing.

2.6k·MCP Servers·Open source