graphify: what it is, what problem it solves & why it's gaining traction

What it solves

Graphify maps an entire project—including code, documentation, PDFs, images, and videos—into a queryable knowledge graph. This eliminates the need to manually grep through files to understand complex project architectures or find connections between disparate components.

How it works

Graphify uses a combination of local AST extraction (via tree-sitter for code) and AI model APIs (for non-code assets) to identify entities and relationships. It can be integrated as a "skill" into various AI coding assistants (like Claude Code, Cursor, and GitHub Copilot), allowing the assistant to query the graph directly using commands like /graphify query instead of reading raw files one by one.

Who it’s for

Developers and architects who need to navigate large, complex codebases and documentation sets, as well as teams using AI coding assistants who want to provide their tools with a structured memory layer of their project.

Highlights

• Broad File Support: Handles 36+ tree-sitter grammars for code, as well as PDFs, Office docs, Google Workspace files, and video/audio transcriptions.
• AI Assistant Integration: Native installation for a wide array of platforms including Claude Code, Cursor, Codex, and Aider.
• Knowledge Graph Outputs: Generates an interactive HTML visualization, a detailed GRAPH_REPORT.md with "god nodes" and surprising connections, and a machine-readable graph.json.
• Automated Architecture: Can export Mermaid call-flow diagrams and can be configured to auto-regenerate on git commits via hooks.
• Confidence Tracking: Marks inferred relationships as EXTRACTED, INFERRED, or AMBIGUOUS to ensure transparency in how the graph was built.