Skip to content

Repository files navigation

LearnLoop

LearnLoop is an intelligent learning companion that dynamically builds and expands a visual map of your knowledge, using AI-powered conversations and automated research to help you explore and remember new topics.

Features

  • Interactive Knowledge Graph: Visualize and expand your learning topics through an interactive force-directed graph
  • AI-Powered Voice Conversations: Engage in real-time voice conversations about any topic
  • Automated Research: Get recent news and developments about your topics of interest
  • Personalized Learning: Your learning graph evolves based on your interests and interactions
  • Persistent Memory: All your learning progress is saved and can be accessed anytime

Prerequisites

  • Python 3.9+
  • Node.js 18+
  • Chrome browser (for Dex extension)
  • Supabase account
  • Anthropic API key
  • OpenAI API key

Installation

  1. Clone the repository:
git clone https://github.com/yourusername/learnloop.git
cd learnloop
  1. Set up the backend:
cd backend
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r requirements.txt
  1. Set up the frontend:
cd frontend
npm install
  1. Install the Dex Chrome extension:

    • Visit the Chrome Web Store
    • Install the extension
    • Use Command+J (Mac) to activate Dex
  2. Set up environment variables:

Create .env files in both backend and frontend directories:

Backend .env:

ANTHROPIC_API_KEY=your_anthropic_api_key
SUPABASE_URL=your_supabase_url
SUPABASE_KEY=your_supabase_key

Frontend .env:

NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_supabase_anon_key

Running the Application

  1. Start the backend server:
cd backend
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
python main.py
  1. Start the frontend development server:
cd frontend
npm run dev
  1. Start the Dex MCP server:
cd dex-mcp
python main.py

The application will be available at http://localhost:3000

Project Structure

learnloop/
├── backend/           # Flask backend server
├── frontend/         # Next.js frontend application
├── dex-mcp/         # Browser automation server
└── README.md        # This file

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

About

Dynamically build and expand a visual map of your knowledge using voice and browser agents. Won 1st place in the Personalization and Memory track at AgentHacks 2025.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages