graphify

<p align="center">
  <a href="https://graphifylabs.ai"><img src="https://raw.githubusercontent.com/safishamsi/graphify/v4/docs/logo-text.svg" width="260" height="64" alt="Graphify"/></a>
</p>

<p align="center">
  🇺🇸 <a href="README.md">English</a> | 🇨🇳 <a href="docs/translations/README.zh-CN.md">简体中文</a> | 🇯🇵 <a href="docs/translations/README.ja-JP.md">日本語</a> | 🇰🇷 <a href="docs/translations/README.ko-KR.md">한국어</a> | 🇩🇪 <a href="docs/translations/README.de-DE.md">Deutsch</a> | 🇫🇷 <a href="docs/translations/README.fr-FR.md">Français</a> | 🇪🇸 <a href="docs/translations/README.es-ES.md">Español</a> | 🇮🇳 <a href="docs/translations/README.hi-IN.md">हिन्दी</a> | 🇧🇷 <a href="docs/translations/README.pt-BR.md">Português</a> | 🇷🇺 <a href="docs/translations/README.ru-RU.md">Русский</a> | 🇸🇦 <a href="docs/translations/README.ar-SA.md">العربية</a> | 🇮🇹 <a href="docs/translations/README.it-IT.md">Italiano</a> | 🇵🇱 <a href="docs/translations/README.pl-PL.md">Polski</a> | 🇳🇱 <a href="docs/translations/README.nl-NL.md">Nederlands</a> | 🇹🇷 <a href="docs/translations/README.tr-TR.md">Türkçe</a> | 🇺🇦 <a href="docs/translations/README.uk-UA.md">Українська</a> | 🇻🇳 <a href="docs/translations/README.vi-VN.md">Tiếng Việt</a> | 🇮🇩 <a href="docs/translations/README.id-ID.md">Bahasa Indonesia</a> | 🇸🇪 <a href="docs/translations/README.sv-SE.md">Svenska</a> | 🇬🇷 <a href="docs/translations/README.el-GR.md">Ελληνικά</a> | 🇷🇴 <a href="docs/translations/README.ro-RO.md">Română</a> | 🇨🇿 <a href="docs/translations/README.cs-CZ.md">Čeština</a> | 🇫🇮 <a href="docs/translations/README.fi-FI.md">Suomi</a> | 🇩🇰 <a href="docs/translations/README.da-DK.md">Dansk</a> | 🇳🇴 <a href="docs/translations/README.no-NO.md">Norsk</a> | 🇭🇺 <a href="docs/translations/README.hu-HU.md">Magyar</a> | 🇹🇭 <a href="docs/translations/README.th-TH.md">ภาษาไทย</a> | 🇹🇼 <a href="docs/translations/README.zh-TW.md">繁體中文</a>
</p>

<p align="center">
  <a href="https://safishamsi.gumroad.com/l/qetvlo"><img src="https://img.shields.io/badge/Book-The%20Memory%20Layer-2ea44f?style=flat&logo=gitbook&logoColor=white" alt="The Memory Layer"/></a>
  <a href="https://github.com/safishamsi/graphify/actions/workflows/ci.yml"><img src="https://github.com/safishamsi/graphify/actions/workflows/ci.yml/badge.svg?branch=v4" alt="CI"/></a>
  <a href="https://pypi.org/project/graphifyy/"><img src="https://img.shields.io/pypi/v/graphifyy" alt="PyPI"/></a>
  <a href="https://pepy.tech/project/graphifyy"><img src="https://static.pepy.tech/badge/graphifyy" alt="Downloads"/></a>
  <a href="https://github.com/sponsors/safishamsi"><img src="https://img.shields.io/badge/sponsor-safishamsi-ea4aaa?logo=github-sponsors" alt="Sponsor"/></a>
  <a href="https://www.linkedin.com/in/safi-shamsi"><img src="https://img.shields.io/badge/LinkedIn-Safi%20Shamsi-0077B5?logo=linkedin" alt="LinkedIn"/></a>
</p>

<p align="center">
  <a href="https://star-history.com/#safishamsi/graphify&Date">
    <img src="https://api.star-history.com/svg?repos=safishamsi/graphify&type=Date" alt="Star History Chart" width="600"/>
  </a>
</p>

**An AI coding assistant skill.** Type `/graphify` in Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, VS Code Copilot Chat, Aider, OpenClaw, Factory Droid, Trae, Hermes, Kiro, or Google Antigravity - it reads your files, builds a knowledge graph, and gives you back structure you didn't know was there. Understand a codebase faster. Find the "why" behind architectural decisions.

Fully multimodal. Drop in code, PDFs, markdown, screenshots, diagrams, whiteboard photos, images in other languages, or video and audio files - graphify extracts concepts and relationships from all of it and connects them into one graph. Videos are transcribed with Whisper using a domain-aware prompt derived from your corpus. 25 languages supported via tree-sitter AST (Python, JS, TS, Go, Rust, Java, C, C++, Ruby, C#, Kotlin, Scala, PHP, Swift, Lua, Zig, PowerShell, Elixir, Objective-C, Julia, Verilog, SystemVerilog, Vue, Svelte, Dart).

> Andrej Karpathy keeps a `/raw` folder where he drops papers, tweets, screenshots, and notes. graphify is the answer to that problem - 71.5x fewer tokens per query vs reading the raw files, persistent across sessions, honest about what it found vs guessed.

```
/graphify .                        # works on any folder - your codebase, notes, papers, anything
```

```
graphify-out/
├── graph.html       interactive graph - open in any browser, click nodes, search, filter by community
├── GRAPH_REPORT.md  god nodes, surprising connections, suggested questions
├── graph.json       persistent graph - query weeks later without re-reading
└── cache/           SHA256 cache - re-runs only process changed files
```

Add a `.graphifyignore` file to exclude folders you don't want in the graph:

```
# .graphifyignore
vendor/
node_modules/
dist/
*.generated.py
```

Same syntax as `.gitignore`. You can keep a single `.graphifyignore` at your repo root — patterns work correctly even when graphify is run on a subfolder.

## What's new in v0.5.0

- **`graphify clone <github-url>`** — clone any public GitHub repo and run the full pipeline on it. Clones to `~/.graphify/repos/<owner>/<repo>`, reuses existing clones on repeat runs (`git pull`). Supports `--branch` and `--out`.
- **`graphify merge-graphs`** — combine two or more `graph.json` outputs into one cross-repo graph. Each node is tagged with its source repo. Useful for mapping dependencies across multiple projects.
- **`CLAUDE_CONFIG_DIR` support** — `graphify install` now respects the `CLAUDE_CONFIG_DIR` environment variable when installing the Claude Code skill, instead of always writing to `~/.claude`.
- **Shrink guard** — `to_json()` refuses to overwrite `graph.json` with a smaller graph. Prevents silent data loss when `--update` is called with a partial chunk list.
- **`build_merge()`** — new library function for safe incremental updates: loads existing graph, merges new chunks, optionally prunes deleted-file nodes, never shrinks.
- **Duplicate node deduplication** — `deduplicate_by_label()` collapses nodes that share a normalised label (e.g. from parallel subagents generating `achille_varzi` and `achille_varzi_c4`). Chunk-suffix contamination is also blocked at the prompt level.
- **Bug fixes** — `graphify-out/` is now excluded from source scanning so generated artifacts never trigger false incremental refresh pressure.

## How it works

graphify runs in three passes. First, a deterministic AST pass extracts structure from code files (classes, functions, imports, call graphs, docstrings, rationale comments) with no LLM needed. Second, video and audio files are transcribed locally with faster-whisper using a domain-aware prompt derived from corpus god nodes — transcripts are cached so re-runs are instant. Third, Claude subagents run in parallel over docs, papers, images, and transcripts to extract concepts, relationships, and design rationale. The results are merged into a NetworkX graph, clustered with Leiden community detection, and exported as interactive HTML, queryable JSON, and a plain-language audit report.

**Clustering is graph-topology-based — no embeddings.** Leiden finds communities by edge density. The semantic similarity edges that Claude extracts (`semantically_similar_to`, marked INFERRED) are already in the graph, so they influence community detection directly. The graph structure is the similarity signal — no separate embedding step or vector database needed.

Every relationship is tagged `EXTRACTED` (found directly in source), `INFERRED` (reasonable inference, with a confidence score), or `AMBIGUOUS` (flagged for review). You always know what was found vs guessed.

## Install

**Requires:** Python 3.10+ and one of: [Claude Code](https://claude.ai/code), [Codex](https://openai.com/codex), [OpenCode](https://opencode.ai), [Cursor](https://cursor.com), [Gemini CLI](https://github.com/google-gemini/gemini-cli), [GitHub Copilot CLI](https://docs.github.com/en/copilot/how-tos/copilot-cli), [VS Code Copilot Chat](https://code.visualstudio.com/docs/copilot/overview), [Aider](https://aider.chat), [OpenClaw](https://openclaw.ai), [Factory Droid](https://factory.ai), [Trae](https://trae.ai), [Kiro](https://kiro.dev), Hermes, or [Google Antigravity](https://antigravity.google)

```bash
# Recommended — works on Mac and Linux with no PATH setup needed
uv tool install graphifyy && graphify install
# or with pipx
pipx install graphifyy && graphify install
# or plain pip
pip install graphifyy && graphify install
```

> **Official package:** The PyPI package is named `graphifyy` (install with `pip install graphifyy`). Other packages named `graphify*` on PyPI are not affiliated with this project. The only official repository is [safishamsi/graphify](https://github.com/safishamsi/graphify). The CLI and skill command are still `graphify`.

> **`graphify: command not found`?** Use `uv tool install graphifyy` (recommended) or `pipx install graphifyy` — both put the CLI in a managed location that's automatically on PATH. With plain `pip`, you may need to add `~/.local/bin` (Linux) or `~/Library/Python/3.x/bin` (Mac) to your PATH, or run `python -m graphify` instead. On Windows, pip scripts land in `%APPDATA%\Python\PythonXY\Scripts`.

### Platform support

| Platform | Install command |
|----------|----------------|
| Claude Code (Linux/Mac) | `graphify install` |
| Claude Code (Windows) | `graphify install` (auto-detected) or `graphify install --platform windows` |
| Codex | `graphify install --platform codex` |
| OpenCode | `graphify install --platform opencode` |
| GitHub Copilot CLI | `graphify install --platform copilot` |
| VS Code Copilot Chat | `graphify vscode install` |
| Aider | `graphify install --platform aider` |
| OpenClaw | `graphify install --platform claw` |
| Factory Droid | `graphify install --platform droid` |
| Trae | `graphify install --platform trae