/mellow-minds

Primary LanguageDartMIT LicenseMIT

Mellow Minds

Overview

The Mellow Minds is an open-source project aimed at providing accessible mental health support through artificial intelligence. This application utilizes advanced language models to offer empathetic responses, suggest coping strategies, and provide resources tailored to users' emotional needs.

Problem Statement

Mental health issues, such as anxiety and depression, affect millions worldwide. Many individuals face barriers in accessing immediate support or may feel hesitant to seek professional help due to stigma or cost constraints. This project seeks to bridge this gap by offering a supportive companion that can be accessed anytime and anywhere.

Solution

The Mellow Minds offers the following features:

  • Emotional Support: Users can express their feelings, and the AI responds with empathetic and supportive messages.
  • Resource Recommendations: Links to articles, podcasts, and videos related to mental health based on user interests.
  • Daily Check-ins: Regular prompts to check users' emotional well-being and provide relevant advice.

Technology Stack

  • Language Model: Utilizes GPT-3 or similar for natural language understanding and generation.
  • Backend: n8n for rapid development and validation of user needs.
  • Frontend: Flutter for building cross-platform mobile applications with a responsive and intuitive user interface.
  • Database: PostgreSQL for storing user profiles and interaction histories.
  • Deployment: Docker and Docker Compose for containerization and deployment orchestration.

Contributing:

We welcome contributions from the community! To contribute to the project, please follow our Contributing Guidelines.

Roadmap

Phase 1: Minimum Viable Product (MVP)

  • Implement basic user authentication and profile management using keycloak.
  • Integrate language model for basic emotional support responses.

Phase 2: Enhanced Features

  • Enhance AI responses with sentiment analysis and context awareness.
  • Implement daily check-ins and personalized activity recommendations.
  • Introduce resource recommendations based on user preferences and behavior.

Phase 3: Scaling and Deployment

  • Optimize performance and scalability for increased user base.
  • Transition backend to Express.js or Bun.sh based on user feedback and needs.
  • Deploy backend using Docker containers for easy deployment and maintenance.
  • Implement continuous integration and automated testing for both backend and Flutter frontend.

License

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