This project provides an interactive mind map visualization tool for learning new topics, targeting individuals who want to organize and explore information visually. It leverages AI to generate mind map structures, offering a streamlined way to create and export learning resources.

How It Works

The application is built with Next.js and utilizes React Flow for interactive mind map rendering. It integrates with AI models, supporting both local Ollama instances and external APIs like OpenAI, via the AI SDK. Users can input information, which is then processed by AI to generate a mind map structure, visualized in the UI. The mind map data can be saved locally as JSON or exported as a Markdown file.

Quick Start & Requirements

• Install dependencies: npm install
• Configure environment variables in .env.local (e.g., NEXT_PUBLIC_USE_LOCAL_MODELS, OpenAI API key).
• Run development server: npm run dev
• Requires Node.js.
• For local models, Ollama must be installed and configured.
• Official documentation: https://github.com/aotakeda/learn-thing

Highlighted Details

• Interactive mind map visualization with React Flow.
• Node details displayed in a side sheet.
• Markdown export functionality for learning materials.
• Support for both local (Ollama) and external (OpenAI) AI models.
• UI components from shadcn and Magic UI.

Maintenance & Community

The project appears to be a personal project with no explicit mention of contributors, sponsorships, or community channels in the README.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The README notes that external models are generally faster than local models. Specific model choices for local and external APIs are configurable but default to llama3.1 and gpt-3.5-turbo respectively.