Turn Any Codebase Into a Queryable Knowledge Graph With Graphify

Graphify is an open-source tool designed to map codebases, documentation, SQL schemas, configurations, and PDFs into a queryable knowledge graph. Instead of relying on vector embeddings or grep searches, the tool parses code locally using tree-sitter AST to build a deterministic graph representation.

Core Features and Operation

• Local AST Parsing: Code is processed locally without sending data to external servers, requiring no API key for code-only corpora.
• Explained Edges: Every connection is tagged as either `EXTRACTED` (explicit in the source) or `INFERRED` (resolved by graphify), providing clear provenance.
• Multi-Assistant Support: Integrates with tools like Claude Code, Cursor, Codex, and Gemini CLI through a simple installation command.
• Semantic Pass: Documentation, PDFs, images, and media can be processed via an optional semantic pass using supported AI backends or local options like Ollama.

Installation and Quick Start

Graphify requires Python 3.10+ and a package runner such as `uv` or `pipx`. The official PyPI package is named `graphifyy` (with a double 'y'), while the CLI command remains `graphify`.

1. Install the package using `uv tool install graphifyy` or `pipx install graphifyy`.
2. Run `graphify install` to register the skill with your supported AI coding assistant.
3. Type `/graphify` in your assistant to query the generated knowledge graph.

For team environments and continuous workflows, Graphify Cloud offers always-on memory, cross-repo support, formal verification, and integrations with tracking tools like Jira and Sentry. Users can verify the installation steps, configuration guides, and troubleshooting documentation directly on the official GitHub repository and documentation site.