graphify-dotnet

🔍 Build AI-powered knowledge graphs from any codebase. Understand structure you didn't know was there.

💡 Origin story — This project traces back to Andrej Karpathy's tweet on using LLMs to build personal knowledge bases: ingesting raw sources, compiling them into structured Markdown wikis, and navigating knowledge through graph views instead of keyword search. That idea inspired graphify by @safishamsi, which was then showcased by @socialwithaayan — and that's what kicked off this .NET port.

graphify-dotnet reads your files (code, docs, images), extracts concepts and relationships through AST parsing and AI semantic analysis, builds a knowledge graph with community detection, and exports interactive visualizations. Navigate codebases by structure instead of keyword search.

Quick Start

1. Install

dotnet tool install -g graphify-dotnet

2. Configure

graphify config

This launches an interactive wizard with three options:

• 📋 View current configuration — see what's set
• 🔧 Set up AI provider — pick Azure OpenAI, Ollama, Copilot SDK, or None (AST-only)
• 📂 Set folder to analyze — set your default project folder and export formats

Pick your AI provider (or skip it — AST-only extraction works with zero config), then set the folder to analyze.

3. Run

graphify run

That's it. Open graphify-out/graph.html in your browser to explore the interactive graph.

📖 New here? See the Getting Started guide for a step-by-step walkthrough.

Supported Languages

graphify detects and extracts structure from these file types:

Category	Languages
Code	C#, Python, TypeScript, JavaScript, Go, Rust, Java, C, C++, Ruby, Kotlin, Scala, PHP, Swift, R, Lua, Shell, PowerShell
Config	YAML, JSON, TOML, XML
Docs	Markdown, Plain Text, reStructuredText, AsciiDoc
Media	PDF, PNG, JPEG, WebP, GIF, SVG

No AI provider? No problem. AST-only extraction works with zero config and produces structural graphs from code — classes, functions, imports, and their relationships. AI providers add semantic extraction (conceptual connections, inferred relationships) but are completely optional.

Build from Source

git clone https://github.com/elbruno/graphify-dotnet.git
cd graphify-dotnet
dotnet build graphify-dotnet.slnx
dotnet run --project src/Graphify.Cli -- run .

NuGet Packages

Package	Purpose	Version	Downloads
graphify-dotnet	.NET global tool (graphify)
graphify-dotnet-core	Core graph extraction and pipeline library
graphify-dotnet-sdk	Copilot/AI SDK integration library

Documentation

Topic	Link
Getting Started	docs/getting-started.md
Architecture	ARCHITECTURE.md
Configuration	docs/configuration.md
CLI Reference	docs/cli-reference.md
Worked Example	docs/worked-example.md
Troubleshooting	docs/troubleshooting.md
AI Providers
Azure OpenAI	docs/setup-azure-openai.md
Ollama	docs/setup-ollama.md
Copilot SDK	docs/setup-copilot-sdk.md
Export Formats	docs/export-formats.md
HTML Interactive	docs/format-html.md
JSON	docs/format-json.md
SVG	docs/format-svg.md
Neo4j Cypher	docs/format-neo4j.md
Ladybug	docs/format-ladybug.md
Obsidian Vault	docs/format-obsidian.md
Wiki	docs/format-wiki.md
Report	docs/format-report.md
Other
Watch Mode	docs/watch-mode.md
Global Tool Install	docs/dotnet-tool-install.md

License

This project is licensed under the MIT License. See LICENSE file for details.

👋 About the Author

Hi! I'm ElBruno 🧡, a passionate developer and content creator exploring AI, .NET, and modern development practices.

Made with ❤️ by ElBruno

If you like this project, consider following my work across platforms:

• 📻 Podcast: No Tienen Nombre — Spanish-language episodes on AI, development, and tech culture
• 💻 Blog: ElBruno.com — Deep dives on embeddings, RAG, .NET, and local AI
• 📺 YouTube: youtube.com/elbruno — Demos, tutorials, and live coding
• 🔗 LinkedIn: @elbruno — Professional updates and insights
• 𝕏 Twitter: @elbruno — Quick tips, releases, and tech news

Acknowledgments

• Andrej Karpathy's tweet on LLM-powered personal knowledge bases — the original idea that started the chain.
• This tweet by @socialwithaayan showcasing graphify by @safishamsi — which directly inspired this .NET port.

This project is a .NET 10 port of safishamsi/graphify, reimagined with C# idioms, .NET 10 features, and the Microsoft.Extensions.AI abstraction layer.