Privacy Guardian AI Agent

An intelligent AI agent that analyzes websites in real-time to detect trackers, monitor cookies, calculate privacy risk, and generate legal actions — all powered by Hugging Face's AI models.

Features

• 🔍 Real-time website analysis
• 🔐 Tracker and cookie detection
• 🧠 AI-powered privacy recommendations
• 📊 Privacy risk scoring
• 📝 Legal request generation
• 📁 Report generation and logging

Setup

1. Clone the repository:

git clone <your-repo-url>
cd privacy-guardian-ai

2. Create a virtual environment and install dependencies:

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

3. Create a .env file in the root directory and add your Hugging Face API key:

HUGGINGFACE_API_KEY=your_api_key_here

4. Start the server:

uvicorn main:app --reload

Usage

The API will be available at http://localhost:8000. Here are the main endpoints:

Analyze a URL

curl -X POST "http://localhost:8000/analyze" \
     -H "Content-Type: application/json" \
     -d '{"url": "https://example.com", "generate_legal_request": true}'

Get All Reports

curl "http://localhost:8000/reports"

API Documentation

Once the server is running, visit http://localhost:8000/docs for interactive API documentation.

Components

• main.py: FastAPI application and endpoints
• scanner/: Privacy scanning components
  • network_scanner.py: Detects trackers and network activity
  • cookie_parser.py: Analyzes cookies and their privacy implications
  • risk_engine.py: Calculates privacy risk scores
• llm/: AI integration
  • huggingface_integration.py: Handles LLM interactions

Privacy First

• All analysis is done locally
• No data is stored permanently
• Reports are saved only if explicitly requested
• Uses secure HTTPS for all external requests

License

MIT License