Back to Copilotkit

FemTracker Agent - AI-Powered Women's Health Companion

community/demos_2025/femtracker-agent.md

1.57.010.8 KB
Original Source

FemTracker Agent - AI-Powered Women's Health Companion

2. Use Case

FemTracker Agent is an innovative AI-powered women's health tracking platform that leverages cutting-edge multi-agent technology to provide personalized health insights, cycle predictions, and comprehensive wellness monitoring. The system features 8 specialized AI agents that work together to deliver intelligent health assistance, real-time analytics, and WHO-standard health scoring.

Key Problems Solved:

  • Complex health data tracking and pattern recognition across multiple health domains
  • Lack of personalized, AI-driven health insights and recommendations for women's health
  • Fragmented health management between cycle tracking, fertility, nutrition, and fitness
  • Limited conversational AI assistance for women's health-specific concerns
  • Need for intelligent coordination and orchestration of specialized health agents

3. Technologies Used

Frontend Stack:

  • Next.js 15 (App Router)
  • React 19
  • TypeScript 5
  • CopilotKit (AI Integration & Conversational Interface)
  • TailwindCSS + Custom Design System
  • Radix UI Components
  • Framer Motion

Backend & AI Stack:

  • Python 3.12
  • LangGraph (AI Agent Orchestration)
  • OpenAI GPT-4
  • Supabase PostgreSQL
  • Redis (Performance Optimization)
  • Vercel Blob Storage

Specialized AI Agents:

  • Main Coordinator Agent (CopilotKit Integration)
  • Cycle Tracker Agent
  • Fertility Tracker Agent
  • Symptom Mood Agent
  • Nutrition Guide Agent
  • Exercise Coach Agent
  • Lifestyle Manager Agent
  • Health Insights Agent

4. GitHub + YouTube

Note: Include a screenshot of your demo in action

6. Who Are You?

Chan Meng - AI & Healthcare Technology Developer

LinkedIn: chanmeng666

⭐️ Project README with installation and getting started steps ⭐️👇

<div align="center">

🌸 FemTracker Agent

AI-Powered Women's Health Companion

An innovative women's health tracking platform that leverages cutting-edge AI multi-agent technology to provide personalized health insights, cycle predictions, and comprehensive wellness monitoring.

Built with CopilotKit for seamless conversational AI experience

🚀 Live Demo · 📖 Documentation · 🐛 Issues

</div>

🌟 Introduction

FemTracker Agent is a cutting-edge women's health companion that combines the power of AI multi-agent systems with comprehensive health tracking. Built with CopilotKit integration, it features 8 specialized AI agents that provide personalized health insights, cycle predictions, and wellness monitoring through natural language conversations.

✨ Key Features

🤖 CopilotKit-Powered Conversational AI

  • Natural Language Interface: Seamless conversation with health AI agents
  • Intelligent Agent Coordination: CopilotKit orchestrates 8 specialized health agents
  • Real-time AI Assistance: Instant health guidance and recommendations
  • Context-Aware Responses: AI understands your health history and patterns

📊 AI Multi-Agent Architecture

  • Main Coordinator Agent: Routes queries to specialized agents via CopilotKit
  • Cycle Tracker Agent: Menstrual cycle prediction and pattern analysis
  • Fertility Tracker Agent: Ovulation prediction and conception guidance
  • Symptom Mood Agent: Emotional health and symptom pattern recognition
  • Nutrition Guide Agent: Personalized dietary recommendations
  • Exercise Coach Agent: Cycle-aware fitness guidance
  • Lifestyle Manager Agent: Sleep optimization and stress management
  • Health Insights Agent: AI-powered analytics and correlation analysis

💎 Advanced Health Analytics

  • WHO-Standard Scoring: Medical-grade health metrics (0-100 scores)
  • Predictive Insights: AI-powered trend analysis and health forecasting
  • Correlation Analysis: Identify patterns between lifestyle factors and health
  • Real-time Synchronization: Live updates across all health modules

🚀 Getting Started

Prerequisites

bash
# Required
Node.js 18.0+
Python 3.12+
Supabase Account
OpenAI API Key

# Optional for enhanced performance
Redis

Quick Installation

1. Clone Repository

bash
git clone https://github.com/ChanMeng666/femtracker-agent.git
cd femtracker-agent

2. Frontend Setup

bash
npm install
# or
pnpm install

3. AI Agent Setup

bash
cd agent
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt

Environment Configuration

Frontend (.env.local):

bash
# OpenAI Configuration
OPENAI_API_KEY=your_openai_api_key_here

# Supabase Configuration
NEXT_PUBLIC_SUPABASE_URL=your_supabase_project_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_supabase_anon_key
SUPABASE_SERVICE_ROLE_KEY=your_supabase_service_role_key

# CopilotKit Agent Configuration
NEXT_PUBLIC_COPILOTKIT_AGENT_NAME=main_coordinator
NEXT_PUBLIC_COPILOTKIT_AGENT_DESCRIPTION="AI health companion with specialized agents for women's health tracking"

# Optional: Redis for Performance
REDIS_URL=your_redis_connection_string

Backend (agent/.env):

bash
# OpenAI Configuration
OPENAI_API_KEY=your_openai_api_key_here

Database Setup

Execute SQL files in your Supabase SQL Editor in order:

  1. database/1-database-setup.sql - Core schema
  2. database/2-database-fix.sql - RLS policies
  3. database/6-fertility-tables.sql - Fertility tracking
  4. database/7-recipe-tables.sql - Recipe management
  5. Additional SQL files as needed

Development Mode

Terminal 1 - AI Agent System:

bash
cd agent
langgraph dev

Terminal 2 - Frontend:

bash
npm run dev

Access Application:

🏗️ CopilotKit Integration Architecture

Agent Coordination Flow

mermaid
graph TB
    subgraph "CopilotKit Interface"
        A[User Input] --> B[CopilotKit Provider]
        B --> C[Conversational AI]
    end

    subgraph "Agent Orchestration"
        D[Main Coordinator] --> E{Intelligent Routing}
        E --> F[Specialized Agents]
        F --> G[Health Processing]
    end

    subgraph "Response Generation"
        H[Agent Responses] --> I[CopilotKit State]
        I --> J[User Interface]
    end

    C --> D
    G --> H
    J --> A

CopilotKit Agent Configuration

typescript
// src/app/api/copilotkit/route.ts
const agents = [
  {
    name: "main_coordinator",
    description:
      "Main health coordinator that routes requests to specialized agents",
    graph_id: "main_coordinator",
  },
  {
    name: "cycle_tracker",
    description:
      "Specialized agent for menstrual cycle tracking and predictions",
    graph_id: "cycle_tracker",
  },
  // Additional specialized agents...
];

💬 Usage Examples

Natural Language Health Conversations

Cycle Tracking:

User: "I think my period started today, can you help me track it?"
AI: "I'll help you track your period! Let me log that your cycle started today and update your predictions. Based on your history, your next period is likely around [date]. How is your flow today - light, medium, or heavy?"

Fertility Monitoring:

User: "Am I in my fertile window this week?"
AI: "Based on your cycle data, you're approaching your fertile window! Your predicted ovulation is in 2-3 days. I recommend tracking your BBT and cervical mucus for more accurate predictions. Would you like me to set up reminders?"

Health Insights:

User: "I've been feeling more tired lately, any patterns you notice?"
AI: "I've analyzed your recent data and noticed your fatigue tends to increase during the luteal phase of your cycle, which is normal. Your sleep quality has also decreased by 15% this week. Let me suggest some cycle-aware wellness strategies..."

🎯 Key Benefits

  • 🤖 Conversational AI: Natural language interaction via CopilotKit
  • 🧠 Multi-Agent Intelligence: 8 specialized agents for comprehensive health support
  • 📊 Medical-Grade Analytics: WHO-standard health scoring algorithms
  • 🔒 Privacy-First: Military-grade encryption for all health data
  • 📱 Mobile-Optimized: Progressive Web App with offline capabilities
  • ⚡ High Performance: 95+ Lighthouse score, Redis caching, real-time sync
  • 🌐 Accessible: WCAG 2.1 compliant for inclusive health tracking

🛳 Deployment

Vercel (Frontend)

LangGraph Platform (AI Agents)

bash
cd agent
langgraph up

Manual Deployment

bash
# Install Vercel CLI
npm i -g vercel

# Deploy frontend
vercel --prod

# Deploy AI agents
cd agent && langgraph up

🤝 Contributing

We welcome contributions to advance women's health technology:

  1. Fork the repository
  2. Create feature branch (git checkout -b feature/health-improvement)
  3. Follow development guidelines (TypeScript, accessibility, medical accuracy)
  4. Add comprehensive tests for health modules
  5. Submit pull request with detailed description

Contribution Areas:

  • 🤖 New AI agent capabilities
  • 📊 Health analytics improvements
  • 🎨 UI/UX enhancements
  • 📚 Documentation and guides
  • 🔒 Security and privacy features

📄 License

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

🙏 Acknowledgments

  • CopilotKit Team for providing exceptional AI integration capabilities
  • LangGraph for powerful agent orchestration framework
  • Supabase for robust database and authentication services
  • WHO Guidelines for health standard compliance
  • Open Source Community for advancing women's health technology

🌟 Star History

If you find FemTracker Agent helpful, please consider giving it a star!


<div align="center"> <strong>🌸 Empowering Women's Health Through AI Technology 💖</strong>

<em>Built with CopilotKit • Pioneering the future of conversational healthcare</em>

Star us on GitHub • 🚀 Try Live Demo • 🤖 Explore AI Agents • 🤝 Join Community

Made with ❤️ for women's health empowerment

</div>