Graphify is an AI coding assistant skill designed to transform any folder of code, SQL schemas, R scripts, shell scripts, documentation, papers, images, or videos into a queryable knowledge graph. The tool integrates with multiple AI coding platforms including Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, VS Code Copilot Chat, Aider, and numerous others. By typing a simple command like /graphify in a supported AI assistant, users can map their entire project—combining application code, database schemas, and infrastructure—into a single unified graph structure that can be queried rather than requiring traditional file searching.
The repository is written in Python and is distributed as a PyPI package named graphifyy. Installation is straightforward, requiring Python 3.10 or higher and either uv or pipx as a package manager. The project supports platform-specific installations across a wide range of AI coding assistants, with dedicated install commands for each platform. The tool generates three core output files and can produce readable architecture pages with Mermaid call-flow diagrams. Graphify is a Y Combinator S26 company, indicating significant backing and validation from the startup accelerator.
Enhancement requests, help wanted issues, and bug reports represent the most frequently used issue labels.
The repository is classified by GitGenius across multiple graph-related categories including graph visualization, network analysis, interactive graphs, data exploration, visual analytics, graph algorithms, node relationships, edge rendering, and dynamic layouts. This classification reflects the core functionality of converting code repositories into knowledge graph structures.
The README demonstrates extensive international support with translations available in over 20 languages including Simplified Chinese, Japanese, Korean, German, French, Spanish, Hindi, Portuguese, Russian, Arabic, Persian, Italian, Polish, Dutch, Turkish, Ukrainian, Vietnamese, Indonesian, Swedish, Greek, Romanian, Czech, Finnish, Danish, Norwegian, Hungarian, Thai, Uzbek, Traditional Chinese, and Filipino. This multilingual approach reflects the project's ambition to serve a global developer audience. The project includes comprehensive documentation for installation across different operating systems and provides detailed platform-specific setup instructions for each supported AI coding assistant, making it accessible to developers regardless of their preferred development environment.
