Graphify-Labs/graphify

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

What it solves

AI coding assistants often waste tokens reading entire files to understand a codebase. Graphify builds a knowledge graph of the project (code, docs, PDFs, images, videos) so assistants can query, trace paths, and explain concepts directly against the graph instead of grepping files. This cuts token spend and speeds up understanding.

How it works

Graphify parses code locally with tree-sitter (an AST parser) — deterministic and free, no LLM involved. For non-code files (docs, PDFs, images, video) it optionally uses your assistant's model or a configured API key for a semantic pass. It builds a graph where nodes are concepts and edges have confidence tags (EXTRACTED if explicit in source, INFERRED if resolved). You get three outputs: an interactive graph.html, a GRAPH_REPORT.md, and graph.json for queries. The CLI provides "explain", "path", and "query" commands. It installs as a skill into 20+ AI assistants (Claude Code, Cursor, Codex, etc.).

Who it's for

Developers and teams using AI coding assistants on large or multi-language codebases, monorepos, or projects with mixed file types. Also for teams that want continuous memory across the SDLC via Graphify Cloud, with features like cross-repo links, code review, formal verification, and connectors for Sentry/Jira.

Highlights

  • Local-first code parsing: free, deterministic, nothing leaves your machine.
  • Real graph, not a vector index — no embeddings, no vector store.
  • Every edge tagged EXTRACTED or INFERRED for transparency.
  • Supports 40+ languages via tree-sitter, plus docs, PDFs, images, video/audio.
  • One command installs into 20+ AI assistants.
  • Benchmarks show 0.497 recall@10 with 0 LLM credits on LOCOMO.

Related

  • Project
    garrytan/gstack

    gstack is an open-source framework that turns AI agents into a structured engineering team by providing specialized slash commands for product planning, security auditing, QA, and release management.

  • Project
    openai/codex

    Codex CLI is a local coding agent from OpenAI that allows developers to to run AI-assisted coding directly from their terminal.

  • Project
    nextlevelbuilder/ui-ux-pro-max-skill

    UI UX Pro Max is an open‑source AI skill that generates full design‑system specs (layout, style, colors, fonts, effects, checklist) from a natural‑language request, using 192 industry rules and searchable catalogs. It ships as an npm CLI (`ui-ux-pro-max-cli`) that integrates with many AI coding assistants (Claude, Cursor, Gemini, etc.). The basic version is free and open source; a premium tier adds brand‑identity and AI‑image generation.

  • Project
    github/spec-kit

    Spec Kit is an open-source toolkit that provides structured, repeatable processes for AI coding agents to handle feature development, bug fixing, and project assessment.