vndangkhoa/sys-arc-visl repository overview

⁠🔮 SysVis.AI - System Design Visualizer

AI-Powered Diagram Editor — Transform ideas into beautiful, interactive flowcharts using natural language, images, or Mermaid code.

⁠✨ Features

• 🤖 AI-Powered Generation — Generates complex diagrams from text prompts using Qwen3-0.6B (local browser) or Cloud AI.
• 👁️ Vision-to-Diagram — ViT-GPT2 powered analysis converts screenshots and sketches into editable layouts entirely in the browser.
• 🖌️ Unified Toolkit — A clean, consolidated toolbar for critical actions (Zoom, Layout, Pan/Select) keeps the canvas "void-like".
• 🗺️ MiniMap Overlay — Navigational aid for large diagrams, unobtrusively positioned in the bottom-right.
• 💡 Smart Guidance — Context-aware tips and rotation suggestions when looking at empty space.
• 📝 Theme-Aware Code Editor — Monaco editor that automatically syncs with your Light/Dark aesthetic.
• 🎨 "Void" Aesthetic — Premium glassmorphism design with deep blur effects and cinematic transitions.
• ⏪ Undo/Redo — Full history support with time-travel capabilities for safe editing.
• 📐 Optimized Layout — Enhanced Dagre layout engine with smart spacing to prevent overlapping text.

⁠🚀 Quick Start

⁠🐳 Docker (Recommended)

docker run -d -p 8338:80 vndangkhoa/sys-arc-visl:latest

Open http://localhost:8338⁠ in your browser.

⁠💻 Local Development

# Clone the repository
git clone https://github.com/vndangkhoa/kv-graph.git
cd kv-graph

# Install dependencies
npm install

# Start development server
npm run dev

Open http://localhost:5173⁠ in your browser.

⁠Prerequisites

• Node.js 18+
• npm or pnpm
• WebGPU-compatible browser (Chrome 113+, Edge) for In-Browser AI

⁠🧠 AI Configuration

KV-Graph supports a Local-First AI architecture, running powerful models directly in your browser via WebGPU.

⁠🌐 In-Browser Mode (Privacy First)

Runs entirely on your device. No data leaves your machine.

Note: First-time load requires downloading model weights.

⁠☁️ Cloud Mode (Fast & Powerful)

Connect to external providers for enhanced capabilities.

Configure your AI provider in Settings (⚙️ icon).

⁠📁 Project Structure

kv-graph/
├── src/
│   ├── components/        # React components
│   │   ├── nodes/         # Custom React Flow nodes
│   │   ├── edges/         # Custom React Flow edges
│   │   ├── editor/        # Monaco Code Editor
│   │   └── ui/            # UI Kit (Glassware)
│   ├── hooks/             # Custom React hooks
│   ├── lib/               # Core Logic
│   │   ├── aiService.ts   # AI Orchestrator
│   │   ├── webLlmService.ts # Local LLM Engine (Qwen3)
│   │   ├── visionService.ts # Local Vision Engine (ViT-GPT2)
│   │   └── layoutEngine.ts # Dagre Auto-Layout
│   ├── pages/             # Route pages
│   ├── store/             # Zustand Global State
│   └── types/             # TypeScript interfaces
├── public/                # Static assets
├── Dockerfile             # Docker build
└── docker-compose.yml     # Docker Compose

⁠🛠️ Tech Stack

⁠📤 Export Formats

⁠⌨️ Keyboard Shortcuts

⁠🗺️ Roadmap

• Undo/Redo history
• Browser-based AI (WebLLM + Transformers.js)
• Vision-to-Diagram (ViT-GPT2)
• Cloud AI integration (Gemini, OpenAI)
• Collaborative editing
• Plugin system

⁠📄 License

MIT License — see LICENSE⁠ for details.

⁠🙏 Acknowledgments

• React Flow⁠ — Powerful diagram library
• Mermaid.js⁠ — Diagram syntax inspiration
• WebLLM⁠ — Browser-based LLM inference
• Transformers.js⁠ — Browser ML models
• Tailwind CSS⁠ — Utility-first styling

Made with ❤️ by vndangkhoa⁠