Graphify
Open-Source Knowledge Graph Skill

Graphify — Knowledge Graphs
for AI Coding Assistants

Graphify is an open-source skill that helps AI coding assistants understand multi-modal codebases by building a queryable knowledge graph from code, docs, papers and diagrams.

Click to Use Graphify MCP Free

Source-reviewed directory

Find MCP servers for real development work

Compare transport, runtime, client support, setup effort, and access risks before connecting an AI agent.
Explore MCP servers

Explore Graphified trending repositories

Open real Graphify outputs from current GitHub Trending projects. Preview the graph without leaving the homepage, then jump into a repo detail page for the full report.

100 repos 854,079 nodes 1,932,930 edges

Showing 24 of 100 repositories

AI-powered job application framework built on Claude Code. Fork it, fill in your profile, and let Claude evaluate jobs, tailor CVs, write cover letters, and prepare you for interviews.

485 nodes · 653 edges · 30 communities
TypeScript Small graph
View details

Production-grade engineering skills for AI coding agents.

86 nodes · 106 edges · 14 communities
JavaScript Small graph
View details

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

28,178 nodes · 57,385 edges · 1,291 communities
Rust Large graph
View details

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

1,818 nodes · 4,381 edges · 93 communities
TypeScript Medium graph
View details

Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB

14,403 nodes · 26,925 edges · 1,106 communities
TypeScript Large graph
View details

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

10,340 nodes · 20,546 edges · 467 communities
Python Large graph
View details

📼 The missing YouTube and YouTube Music macOS app

8,514 nodes · 23,073 edges · 324 communities
Swift Large graph
View details

An agentic skills framework & software development methodology that works.

428 nodes · 614 edges · 58 communities
Shell Small graph
View details

💡 Download the complete source code of any website (including all assets). [ Javascripts, Stylesheets, Images ] using Node.js

32 nodes · 29 edges · 6 communities
HTML Small graph
View details

🐱 跨平台互动桌宠 BongoCat,为桌面增添乐趣!

980 nodes · 1,544 edges · 65 communities
Vue Small graph
View details

流萤,清新美观的 Astro 静态博客主题模板,Material Design 3 风格设计 | Firefly, fresh and aesthetic Astro blog theme template, Material Design 3 Style Design, Secondary development based on Fuwari.

1,494 nodes · 3,365 edges · 92 communities
Astro Medium graph
View details

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

811 nodes · 1,390 edges · 72 communities
Elixir Small graph
View details
zml/zml #16

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

4,638 nodes · 9,095 edges · 271 communities
Zig Medium graph
View details

Improved fzf.vim written in lua

747 nodes · 1,071 edges · 74 communities
Lua Small graph
View details

Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

61 nodes · 93 edges · 8 communities
JavaScript Small graph
View details

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

1,325 nodes · 2,842 edges · 77 communities
Python Medium graph
View details

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai ) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows.

4,859 nodes · 11,535 edges · 206 communities
Rust Medium graph
View details

Repository for skills to assist AI coding agents with .NET and C#

15,085 nodes · 32,267 edges · 974 communities
C# Large graph
View details

Show usage stats for OpenAI Codex and Claude Code, without having to login.

21,039 nodes · 62,127 edges · 771 communities
Swift Large graph
View details
Graph preview

What is Graphify?

Graphify is a multi-modal knowledge graph builder created for AI coding assistants such as Claude Code, OpenAI Codex and OpenCode. By combining Tree-sitter static analysis with LLM-driven semantic extraction, Graphify turns an entire repository — including source code, documentation, research papers and diagrams — into an interactive graph that explains both what the code does and why it was designed that way. The project is maintained by Safi Shamsi, released under the permissive MIT license, and built on widely-trusted libraries including NetworkX and Tree-sitter.

3.7k+GitHub Stars
MITLicense
71.5×Token Reduction
Python 3.10+Runtime

Core Capabilities

Graphify unifies static analysis, semantic extraction and graph clustering into a single skill that any AI coding assistant can invoke.

Multi-Modal Extraction

Parses code (.py, .js, .go, .java, …), Markdown, PDFs and images. Tree-sitter extracts ASTs, call graphs and docstrings; LLMs extract concepts from prose; vision models read diagrams.

Knowledge Graph Build

Merges all extracted nodes and edges into a NetworkX graph and applies the Leiden algorithm for semantic community detection — no vector embeddings required.

God Nodes & Surprises

Identifies the highest-degree "god nodes" at the heart of the system and flags unexpected cross-file or cross-domain connections worth investigating.

Interactive Outputs

Exports an interactive graph.html, a queryable graph.json, and a human-readable GRAPH_REPORT.md audit report.

Assistant Integration

Ships with /graphify, /graphify query, /graphify path and /graphify explain commands for Claude Code, Codex, OpenCode and more.

Secure by Design

Strict input validation: only http/https URLs, size and timeout limits, path containment, HTML-escaped node labels — defending against SSRF, injection and XSS.

Architecture & Pipeline

Graphify is a multi-stage pipeline. Each stage is an isolated module so contributors can extend any step independently.

detect — collect files extract — AST + LLM nodes/edges build — NetworkX graph cluster — Leiden communities analyze — god nodes & surprises report — GRAPH_REPORT.md export — HTML / JSON / Obsidian

Supporting modules include ingest.py for URL fetching, cache.py for semantic caching, security.py for input validation, watch.py for live updates and serve.py for MCP-protocol service.

Install & Run

Install Graphify AI from the repository with Python 3.12 and uv. The package is private-context-mcp; the CLI command is private-context.

# Requires Python 3.12 and uv; run from the Graphify AI repository root
uv sync --extra dev --extra cloud --no-editable \
  --reinstall-package private-context-mcp

# Verify the local installation
uv run --no-sync private-context doctor

# Start the local stdio MCP server
uv run --no-sync private-context serve --transport stdio

The commands use Graphify AI’s locked dependencies and local runtime. Use the hosted console at app.graaph.org when you do not need a local installation.

Worked Examples

The repository ships with reproducible corpora demonstrating Graphify on both small libraries and large mixed code-and-paper collections.

httpx (small)

6 Python files modeling an HTTP transport layer. Result: 144 nodes, 330 edges, 6 communities. God nodes: Client, AsyncClient, Response, Request. Surprise edge: DigestAuth → Response.

Karpathy mixed corpus

3 GPT framework repos + 5 attention papers + 4 diagrams (~52 files, ~92k words). Result: 285 nodes, 340 edges, 53 communities. Average query cost ~1.7k tokens vs ~123k naive — a 71.5× reduction.

Comparison

How Graphify relates to adjacent open-source projects in the code-intelligence space.

ProjectFocusStrengthLimitation vs Graphify
SourcegraphCross-repo code searchEnterprise-grade navigationNot a knowledge graph; limited design semantics
Code2VecFunction-level embeddingsVector retrieval & classificationNo graph structure, no multi-modal input
Neo4jGeneral graph databasePowerful Cypher queriesDoes not generate graphs from code itself

Security, Licensing & Trust

Graphify is released under the MIT License. Its core dependencies — NetworkX (BSD) and Tree-sitter (MIT) — are all permissive open-source licenses with no conflicts. The project performs no telemetry. The only outbound network call is the semantic-extraction step, which uses your own configured AI model API key; only semantic descriptions of documents are transmitted, never raw source code. URLs are restricted to http/https, downloads are size- and time-bounded, output paths are containment-checked, and node labels are HTML-escaped to prevent SSRF, Cypher injection and XSS.

Frequently Asked Questions

Does Graphify send my code to a third-party model?

No. Graphify only sends semantic descriptions of documents and diagrams to the AI model you have already configured in your assistant — never raw source files.

Which AI coding assistants are supported?

Claude Code, OpenAI Codex and OpenCode are supported out of the box via dedicated skill-*.md manifests. Any assistant that can call shell commands can invoke graphify.

How large a codebase can Graphify handle?

Tree-sitter parsing and NetworkX construction scale linearly with code size. On a ~500k-word corpus, BFS subgraph queries stay around ~2k tokens versus ~670k naive — preserving compression at scale.

Is Graphify free for commercial use?

Yes. Graphify is MIT-licensed and free for both personal and commercial use.