This project provides an AI-powered tool for generating professional charts and diagrams from natural language descriptions, integrated seamlessly with the Excalidraw editor. It targets users who need to quickly visualize concepts, workflows, or data structures, offering a significant time-saving benefit by automating the initial creation process and allowing for immediate, flexible manual refinement.

How It Works

The core approach leverages advanced Large Language Models (LLMs) to interpret user prompts, translating natural language requests into structured diagrams. A key differentiator is its "original connection algorithm," which intelligently calculates optimal placement for smart arrows, ensuring clarity and minimizing line crossings. Generated diagrams are fully compatible with Excalidraw, allowing users to freely edit, style, and add details post-generation, merging AI efficiency with manual control.

Quick Start & Requirements

To begin, users must configure an AI provider (OpenAI or Anthropic) and input their API Key via the "Configure LLM" button. The recommended model for optimal results is claude-sonnet-4.5. Configuration is saved locally for privacy. For local deployment, clone the repository, install dependencies using pnpm install, and start the development server with pnpm dev. The application is accessible at http://localhost:3000.

Highlighted Details

• AI-driven chart generation from natural language descriptions.
• Proprietary smart arrow optimization algorithm for clear connections.
• Supports over 20 chart types, including flowcharts, architecture diagrams, ER diagrams, and mind maps.
• Full integration with Excalidraw for seamless editing and customization.
• "Out-of-the-box" functionality requiring only an AI API key.
• Privacy-focused: All configuration is stored locally in the browser.

Maintenance & Community

Specific details regarding maintainers, community channels (like Discord or Slack), or a public roadmap are not present in the provided README.

Licensing & Compatibility

The project is released under the MIT License, which is generally permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

Functionality is dependent on the availability and cost of external AI API keys from providers like OpenAI or Anthropic. The quality of generated output is directly tied to the chosen LLM. Local development requires pnpm as the package manager.