graphify: a codebase-to-knowledge-graph mapper that integrates with AI coding assistants for architectural querying

What it solves

Graphify transforms complex project directories—containing code, documentation, PDFs, images, and videos—into a queryable knowledge graph. This eliminates the need to manually grep through files or read every document to understand a codebase's architecture and connections.

How it works

Graphify analyzes project files using a combination of local AST extraction (via tree-sitter for code) and AI model APIs for other media types. It maps relationships between concepts, files, and assets, producing three main outputs: an interactive HTML visualization, a detailed Markdown report (GRAPH_REPORT.md), and a graph.json file for programmatic querying. 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 rather than reading raw files.

Who it’s for

Developers and architects who need to quickly map out unfamiliar codebases, track dependencies across different file types, and provide AI coding assistants with a structured understanding of a project's high-level architecture.

Highlights

• Broad File Support: Handles 36+ programming languages, Salesforce Apex, Terraform, PDFs, Office docs, and even video/audio transcriptions.
• AI Assistant Integration: Installs as a native skill across dozens of platforms (Claude Code, Cursor, Aider, etc.) with "always-on" guidance via hooks or config files.
• Architectural Insights: Identifies "God nodes" (central concepts), surprising cross-module connections, and extracts design rationale from comments like # WHY: or # NOTE:.
• Automated Documentation: Can export Mermaid call-flow diagrams and generate a Markdown wiki from the graph.