graphify: a knowledge graph generator for codebases and documentation that integrates with AI coding assistants

What it solves

Graphify maps a project's entire codebase, documentation, and media files into a searchable knowledge graph. This allows developers to query the structure and relationships of a project instead of manually searching through files using grep or reading source code line-by-line.

How it works

Graphify uses tree-sitter AST (Abstract Syntax Tree) to parse code locally and deterministically without requiring an LLM. For non-code assets like PDFs, images, and videos, it performs a semantic pass using a configured AI model. It then generates a graph.json file containing the full graph, a graph.html for interactive visualization, and a GRAPH_REPORT.md for high-level architectural highlights.

Who it’s for

Developers using AI coding assistants (such as Claude Code, Cursor, GitHub Copilot, or Aider) who need a more structured way to navigate and understand complex codebases.

Highlights

• Local-first code parsing: Code is parsed locally via tree-sitter, ensuring no code leaves the machine.
• Multi-modal mapping: Integrates code, docs, PDFs, images, and audio/video into a single graph.
• Explainable edges: Every connection is tagged as either EXTRACTED (explicit in source) or INFERRED (derived by resolution).
• AI Assistant Integration: Can be registered as a skill for 20+ AI coding assistants to nudge them toward querying the graph instead of raw files.
• Broad Language Support: Resolves cross-file links (calls, imports, inherits) across approximately 40 languages.