graphify

English | 简体中文 | 日本語 | 한국어

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.

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

---

GitHub에서 전체 내용 보기