DayuanJiang/next-ai-draw-io

A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visualization.

What it solves

It simplifies the creation and modification of complex diagrams by allowing users to generate them using natural language instead of manually dragging and dropping elements. It also solves the problem of converting static documents (PDFs, text files) or existing images into editable draw.io diagrams.

How it works

The application is built with Next.js and uses the Vercel AI SDK to connect to various LLMs. The AI processes user prompts and generates the specific XML format required by draw.io to render the diagrams. It integrates react-drawio for the visual representation and manipulation of these diagrams.

Who it’s for

  • Architects and Engineers: For quickly sketching cloud architecture (AWS, GCP, Azure) or system designs.
  • Technical Writers: For converting documentation into visual flowcharts.
  • Developers: For creating rapid prototypes of logic flows or authentication processes.

Highlights

  • Multi-Modal Input: Create diagrams from text prompts, uploaded images, or PDF/text documents.
  • MCP Server Support: Integrates with AI agents like Claude Desktop, Cursor, and VS Code via the Model Context Protocol.
  • Broad Provider Support: Compatible with a wide range of LLMs including OpenAI, Anthropic, Google, DeepSeek, and Ollama.
  • Advanced Visuals: Supports animated connectors and displays the AI's reasoning process for supported models.
  • Version Control: Includes a diagram history feature to track and restore previous versions.

Related

  • Project
  • Project
  • Project
  • Project
  • Project