{"name":"Graphify: Transform Your Codebase into a Queryable Knowledge Graph","description":"Graphify is an innovative AI coding assistant skill that converts any codebase, documentation, and even multimedia files into a queryable knowledge graph. This powerful tool allows developers to navigate complex projects by querying relationships between components, rather than manually searching through files. It integrates seamlessly with popular AI assistants, providing deep insights and streamlining development workflows.","github":"https://github.com/safishamsi/graphify","url":"https://osrepos.com/repo/safishamsi-graphify","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/safishamsi-graphify","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/safishamsi-graphify.md","json":"https://osrepos.com/repo/safishamsi-graphify.json","topics":["knowledge-graph","AI","Python","Developer Tools","Code Analysis","RAG","Graphrag","Claude Code"],"keywords":["knowledge-graph","AI","Python","Developer Tools","Code Analysis","RAG","Graphrag","Claude Code"],"stars":null,"summary":"Graphify is an innovative AI coding assistant skill that converts any codebase, documentation, and even multimedia files into a queryable knowledge graph. This powerful tool allows developers to navigate complex projects by querying relationships between components, rather than manually searching through files. It integrates seamlessly with popular AI assistants, providing deep insights and streamlining development workflows.","content":"## Introduction\nGraphify is an advanced AI coding assistant skill designed to revolutionize how developers interact with their codebases. It takes any folder of code, SQL schemas, R scripts, shell scripts, documents, papers, images, or videos and transforms them into a queryable knowledge graph. This means you can have your application code, database schema, and infrastructure all represented in one interconnected graph, making complex projects easier to understand and navigate. Graphify integrates with a wide range of AI coding assistants, including Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and many more.\n\n## Installation\nGetting started with Graphify is straightforward.\n\n### Prerequisites\nEnsure you have Python 3.10+ installed. For package management, `uv` is recommended, or `pipx` as an alternative.\n\n*   **Python**: 3.10+\n*   **uv (recommended)**: `curl -LsSf https://astral.sh/uv/install.sh | sh`\n*   **pipx (alternative)**: `pip install pipx`\n\n### Step 1: Install the package\nThe official PyPI package is `graphifyy` (note the double-y), though the CLI command remains `graphify`.\n\nbash\n# Recommended (uv puts graphify on PATH automatically):\nuv tool install graphifyy\n\n# Alternatives:\npipx install graphifyy\npip install graphifyy\n\n\n### Step 2: Register the skill with your AI assistant\nAfter installation, register Graphify with your preferred AI assistant.\n\nbash\ngraphify install\n\n\nNow, open your AI assistant and type `/graphify .` to start mapping your project. For platform-specific installations, refer to the official documentation.\n\n## Examples\nGraphify simplifies project exploration with intuitive commands.\n\n### Build a Knowledge Graph\nTo generate a knowledge graph for your current directory, simply run:\n\nbash\n/graphify .\n\n\nThis command will produce three key files in the `graphify-out/` directory:\n*   `graph.html`: An interactive visualization of your graph, viewable in any browser.\n*   `GRAPH_REPORT.md`: A summary of highlights, key concepts, surprising connections, and suggested questions.\n*   `graph.json`: The full graph data, which you can query directly.\n\n### Querying the Graph\nInstead of grepping through files, ask your graph questions:\n\nbash\n/graphify query \"what connects auth to the database?\"\n\n\n### Export Call-Flow Diagrams\nGenerate readable architecture pages with Mermaid call-flow diagrams:\n\nbash\ngraphify export callflow-html\n\n\n### Add External Content\nIntegrate external resources like research papers or videos into your graph:\n\nbash\n/graphify add https://arxiv.org/abs/1706.03762\n/graphify add <youtube-url>\n\n\n## Why Use It\nGraphify transforms how you understand and interact with complex codebases.\n\n### Deep Codebase Understanding\nIt provides a high-level overview of your project's architecture, revealing \"God nodes\" (most-connected concepts) and \"surprising connections\" between different modules or files. This helps in quickly grasping the core logic and interdependencies.\n\n### AI-Powered Insights\nThe generated `GRAPH_REPORT.md` offers AI-curated insights, including suggested questions the graph is uniquely positioned to answer, and explanations for code sections (from inline comments and docstrings). Every inferred relationship is tagged with `EXTRACTED`, `INFERRED`, or `AMBIGUOUS`, giving you confidence in the data.\n\n### Comprehensive File Support\nGraphify handles a wide array of file types, ensuring a holistic view of your project:\n*   **Code**: 31 languages including Python, TypeScript, Go, Java, C++, SQL, and more.\n*   **Docs**: Markdown, HTML, TXT, RST, YAML.\n*   **Office**: `.docx`, `.xlsx` (with optional extras).\n*   **PDFs**: `.pdf`.\n*   **Images**: `.png`, `.jpg`, `.webp`, `.gif`.\n*   **Video / Audio**: `.mp4`, `.mov`, `.mp3`, `.wav`, and YouTube URLs (with optional extras).\n\n### Seamless AI Assistant Integration\nBy registering Graphify as a skill, your AI assistant can leverage the knowledge graph for codebase questions, preferring scoped queries over raw file searches, significantly enhancing its utility and accuracy.\n\n## Links\n*   **GitHub Repository**: [https://github.com/safishamsi/graphify](https://github.com/safishamsi/graphify){:target=\"_blank\"}\n*   **Official Website**: [https://graphifylabs.ai](https://graphifylabs.ai){:target=\"_blank\"}\n*   **License**: MIT License","metrics":{"detailViews":6,"githubClicks":3},"dates":{"published":null,"modified":"2026-05-18T23:17:56.000Z"}}