LearnFlow AI

AI Study Agent | Transforms docs, slides, and text into interactive study packs

Report Bug · Request Feature

LearnFlow AI is an intelligent study companion designed to break down dense course material into clear, structured study packs. It combines document understanding with smart content generation to make studying easier, faster, and more organized.

The goal is simple: take any class topic, syllabus, or set of notes and transform it into a comprehensive resource—including summaries, key concepts, practice problems, flashcards, and curated external links.

Under the hood, LearnFlow isn't just a wrapper. It utilizes an agentic workflow (built with Pydantic AI) to orchestrate context, validate outputs, and ensure that every study pack is structured perfectly for the user's needs.

(back to top)

• Agentic Workflow: Powered by Pydantic AI to intelligently parse, chunk, and synthesize complex course materials rather than just summarizing text.
• Multi-Modal Ingestion: Seamlessly processes PDFs, DOCX, PowerPoints, and raw text input to generate unified study guides.
• Structured Knowledge Output: Transforms unstructured lectures into strict, type-safe JSON formats for consistent summaries, flashcards, and quizzes.
• Distraction-Free UX: A clean, modern interface built with React + TypeScript and Tailwind CSS, designed to reduce cognitive load.
• Smart Resource Curation: Automatically generates "Further Reading" sections by identifying key topics and retrieving relevant external context.
• Resilient Error Handling: Backend-ready validation ensures that even large or complex files are processed smoothly without crashing the agent.

(back to top)

(back to top)

To get a local copy up and running follow these simple steps.

• Python 3.11+

  pyenv install python-3.11.8

• Node.js 18+ and npm

  node --version
  npm --version

1. Get a free Gemini API Key at https://aistudio.google.com/app/apikey
2. Clone the repo

   git clone https://github.com/alvagarciia/learnflow-ai.git
   cd learnflow-ai

3. Backend Setup

   Create a virtual environment

   Recommended to avoid dependency conflicts

   cd backend
   python -m venv venv
   source venv/bin/activate    # Mac/Linux
   venv\Scripts\activate       # Windows

Install dependencies

   pip install -r requirements.txt

Create a .env file in the backend directory and add your API key

   GEMINI_API_KEY=your_api_key_here

4. Frontend Setup

   Open a new terminal and navigate to frontend

   cd frontend

Install dependencies

   npm install

Create a .env file in the frontend directory

   VITE_API_URL=http://localhost:5000/api

5. Change git remote url to avoid accidental pushes to base project

   Only necessary if you forked or cloned this project to make your own version

   git remote set-url origin github_username/learnflow-ai
   git remote -v # confirm the changes

You'll need two terminal windows running simultaneously:

Terminal 1 - Backend:

cd backend
source venv/bin/activate    # Mac/Linux (or venv\Scripts\activate on Windows)
python app.py

Backend will run on http://localhost:5000

Terminal 2 - Frontend:

cd frontend
npm run dev

Frontend will run on http://localhost:5173

Visit http://localhost:5173 in your browser to use the application.

(back to top)

Once started, users can visit the site and start generating study material instantly — no login required. They can:

1. Enter a topic, chapter, or class concept
2. (Optionally) upload files such as syllabi, notes, or slides
3. Select which type of outputs they want included
4. Generate a study pack in seconds

Each study pack is designed for real learning — with key points, summaries, flashcards, and problems that help students understand faster. The system is optimized to handle both short inputs and large documents, while keeping latency minimal.

(back to top)

(back to top)

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

Distributed under the MIT License. See LICENSE for more information.

(back to top)

Alvaro Garcia - LinkedIn @alvaro-garciam - alvaroedgamu@gmail.com

Project Link: https://github.com/alvagarciia/learnflow-ai

(back to top)