dayuan.jiang
00ebf91b90
A user's approval-workflow flowchart came out with the return arrow drawn straight through two unrelated steps, and a second report showed arrows leaving a box and bending straight back across it. Measured over 250 generated flowcharts (2722 edges): 347 arrows crossed an unrelated box and 215 waypoints landed inside a shape. Four defects, each measured in isolation: 1. The invisible layer containers draw_graph emits were handed to the router as frames, so every clean return path was rejected for "trespassing" on a border that is not drawn, and the fallback cut through two boxes. Excluding invisible containers: 347 -> 218 crossing arrows, no diagram made worse. 2. The router chose the horizontal-vs-vertical axis BEFORE searching, so when the only clean corridor ran along the other axis it was never looked at. A complete two-bend candidate generator that tries both trunk axes, all four sides at each end, and the port fractions: 218 -> 27. (An independent ablation measured the axis pre-choice alone at a 40% per-edge failure rate.) 3. Nothing stopped a route's first leg from turning back across its own source shape - the obstacle test exempts an edge's own endpoints, and must, since the line has to touch them. A terminal-leg rule refuses such routes outright: 215 -> 4 hooks. 4. A two-bend search cannot express the staircase needed when a box sits directly between two vertically aligned nodes (21 of the last 27 crossings). Added the orthogonal visibility graph + A* from Wybrow, Marriott & Stuckey, "Orthogonal Connector Routing" (GD 2009) - the libavoid algorithm - as the backstop when the candidate search finds nothing. The interesting-points grid is provably sufficient: any valid route shrinks onto it without getting longer or gaining bends. The A* state is (point, incoming direction) with libavoid's bend cost of 10, and the admissible bends-remaining heuristic, so it returns a cheapest route, not merely a route. Implemented from the paper, not ported. After all four: 0 crossing arrows and 0 hooks over the same 250 diagrams, page area unchanged (494k px^2 mean), 260ms for the whole corpus, mean 0.82 bends per edge. The shape ladder still runs first, so routes that were already clean are byte-identical. Also post-nudge validation now checks the whole path (the nudge pass only reverts the single segment it moved, judged in isolation) and restores the search's route if nudging made it dirty.
Next AI Draw.io
A Next.js web application that integrates AI capabilities with draw.io diagrams. Create, modify, and enhance diagrams through natural language commands and AI-assisted visualization.
Note: Thanks to
ByteDance Doubao sponsorship, the demo site now uses the powerful glm-4.7 model!
https://github.com/user-attachments/assets/9d60a3e8-4a1c-4b5e-acbb-26af2d3eabd1
Table of Contents
- Next AI Draw.io
Examples
Here are some example prompts and their generated diagrams:
|
Animated transformer connectors Prompt: Give me a **animated connector** diagram of transformer's architecture. 
|
|
|
RAG Technique Diagram Prompt: Generate a RAG architecture diagram for **chat application**. Use connected diagram for data ingestion 
|
Authentication using React and AWS Prompt: Generate authentication process using React with **AWS**. Use Serverless architecture. 
|
|
Open Innovation Prompt: Create visualization of Henry Chesbrough's Open Innovation model. 
|
Cat sketch Prompt: Draw a cute cat for me. 
|
Features
- LLM-Powered Diagram Creation: Leverage Large Language Models to create and manipulate draw.io diagrams directly through natural language commands
- Image-Based Diagram Replication: Upload existing diagrams or images and have the AI replicate and enhance them automatically
- PDF & Text File Upload: Upload PDF documents and text files to extract content and generate diagrams from existing documents
- AI Reasoning Display: View the AI's thinking process for supported models (OpenAI o1/o3, Gemini, Claude, etc.)
- Diagram History: Comprehensive version control that tracks all changes, allowing you to view and restore previous versions of your diagrams before the AI editing.
- Interactive Chat Interface: Communicate with AI to refine your diagrams in real-time
- Cloud Architecture Diagram Support: Specialized support for generating cloud architecture diagrams (AWS, GCP, Azure)
- Computed Layout: For architecture diagrams, flowcharts, swimlane/BPMN diagrams, sequence diagrams, mind maps and org charts, the AI declares only the structure — what contains what, or what points at what — and the app computes every coordinate, size and arrow route. Containers always fit their contents, siblings never overlap, and arrows are routed around the shapes they would otherwise cross. Anything you then move or recolour by hand is read back as part of the diagram, so a later edit does not undo it.
- Animated Connectors: Create dynamic and animated connectors between diagram elements for better visualization
MCP Server
Use Next AI Draw.io with AI agents like Claude Desktop, Cursor, and VS Code via MCP (Model Context Protocol).
{
"mcpServers": {
"drawio": {
"command": "npx",
"args": ["@next-ai-drawio/mcp-server@latest"]
}
}
}
Claude Code CLI
claude mcp add drawio -- npx @next-ai-drawio/mcp-server@latest
Then ask Claude to create diagrams:
"Create a flowchart showing user authentication with login, MFA, and session management"
The diagram appears in your browser in real-time!
See the MCP Server README for VS Code, Cursor, and other client configurations.
Getting Started
Try it Online
No installation needed! Try the app directly on our demo site:
Bring Your Own API Key: You can use your own API key to bypass usage limits on the demo site. Click the Settings icon in the chat panel to configure your provider and API key. Your key is stored locally in your browser and is never stored on the server.
Desktop Application
Download the native desktop app for your platform from the Releases page:
Supported platforms: Windows, macOS, Linux.
Run with Docker
Installation
- Clone the repository:
git clone https://github.com/DayuanJiang/next-ai-draw-io
cd next-ai-draw-io
npm install
cp env.example .env.local
See the Provider Configuration Guide for detailed setup instructions for each provider.
- Run the development server:
npm run dev
- Open http://localhost:6002 in your browser to see the application.
Deployment
Deploy to EdgeOne Pages
You can deploy with one click using Tencent EdgeOne Pages.
Deploy by this button:
Check out the Tencent EdgeOne Pages documentation for more details.
Additionally, deploying through Tencent EdgeOne Pages will also grant you a daily free quota for DeepSeek models.
Deploy on Vercel
The easiest way to deploy is using Vercel, the creators of Next.js. Be sure to set the environment variables in the Vercel dashboard as you did in your local .env.local file.
See the Next.js deployment documentation for more details.
Deploy on Cloudflare Workers
Multi-Provider Support
- ByteDance Doubao
- AWS Bedrock (default)
- OpenAI
- Anthropic
- Google AI
- Google Vertex AI
- Azure OpenAI
- Ollama
- OpenRouter
- AIHubMix
- DeepSeek
- SiliconFlow
- ModelScope
- SGLang
- Vercel AI Gateway
All providers except AWS Bedrock and OpenRouter support custom endpoints.
📖 Detailed Provider Configuration Guide - See setup instructions for each provider.
Server-Side Multi-Model Configuration
Administrators can configure multiple server-side models that are available to all users without requiring personal API keys. Configure via AI_MODELS_CONFIG environment variable (JSON string) or ai-models.json file. For a single-provider quick setup, list comma-separated model IDs in AI_MODEL.
Admin Panel
Set the ADMIN_PASSWORD environment variable and visit /admin to manage server settings (models, access codes, features, observability, quota) from a web panel instead of hand-editing .env.
📖 Admin Panel Guide — setup, precedence rules, and notes.
Model Requirements: This task requires strong model capabilities for generating long-form text with strict formatting constraints (draw.io XML). Recommended models include Claude Sonnet 4.5, GPT-5.1, Gemini 3 Pro, and DeepSeek V3.2/R1.
Note that the claude series has been trained on draw.io diagrams with cloud architecture logos like AWS, Azure, GCP. So if you want to create cloud architecture diagrams, this is the best choice.
How It Works
The application uses the following technologies:
- Next.js: For the frontend framework and routing
- Vercel AI SDK (
ai+@ai-sdk/*): For streaming AI responses and multi-provider support - react-drawio: For diagram representation and manipulation
Diagrams are represented as XML that can be rendered in draw.io. The AI processes your commands and generates or modifies this XML accordingly.
Support & Contact
Special thanks to ByteDance Doubao for sponsoring the API token usage of the demo site! Register on the ARK platform to get 500K free tokens for all models!
If you find this project useful, please consider sponsoring to help me host the live demo site!
For support or inquiries, please open an issue on the GitHub repository or contact the maintainer at:
- Email: me[at]jiang.jp
FAQ
See FAQ for common issues and solutions.