<we need a logo :)>

Preserver is an open-source project made to help you create a digital twin of yourself. By gathering and storing your personal data locally, Preserver empowers you to train future Language Learning Models (LLMs) to respond as you would, creating a unique digital representation of your thoughts and personality.

• 🔒 Privacy-First: All data is stored locally, giving you full control over your information.
• 🧠 Customizable Questions: Easily add or modify questions to capture your unique perspective.
• 💾 LLM-Ready Format: Data is saved in a format optimized for future LLM training.
• 🔄 Continuous Learning: Keep adding to your dataset to improve your digital twin over time.
• 🚀 Open for Contributions: We encourage community involvement to enhance the project.

• Python 3.7+
• pip

1. Clone the repository:

   git clone https://github.com/Gogolian/preserver.git
   cd preserver
   

2. Install the required packages:

   pip install gradio
   

3. Run the application:

   python app.py
   

4. Open your web browser and navigate to the URL provided in the terminal.

1. Start the app and enter your username.
2. Answer the series of questions presented to you.
3. Your responses are saved locally in an LLM-friendly format.
4. Use your gathered data to train a personalized LLM in the future.

We welcome contributions from the community! Here are some ways you can help:

• Add new questions to the questions directory
• Improve the user interface
• Enhance data storage and retrieval methods
• Suggest new features

Please read our CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.

• Script to agregate answers into a single file per user
• Pure html/js version to run locally without python
• Add voice input
• Multilingual support
• Integration with popular LLM training frameworks
• Mobile app for on-the-go data collection
• Improved data visualization and management tools
• ???

Preserver is an experimental project in its early stages. The author and contributors hold no liability for the use or misuse of this software. Always be cautious about the personal information you provide and how you use your digital twin.

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

Built with ❤️ by Gogolian and the open-source community.

Remember: Your data, your twin, your future!