A web-based scam detection tool to help Indonesian citizens identify and prevent potential scams through text analysis.
SafeGuard Nusantara is a scam detection application that leverages Google's Gemini AI to analyze text and identify potential scams. It provides real-time analysis and feedback collection to continuously improve its detection capabilities.
- 🔍 Real-time text analysis for scam detection
- 🤖 AI-powered threat assessment using Google Gemini
- 📊 Three-level threat classification (Aman, Mencurigakan, Berbahaya)
- 💬 Detailed explanation for each analysis
- ⭐ User feedback system
- 📱 Mobile-responsive design
- Indonesian citizens
- Anyone who wants to verify suspicious messages
- People who want to learn about common scam patterns
- Frontend: React + TypeScript
- Build Tool: Vite
- UI Framework: Tailwind CSS + shadcn/ui
- AI/ML: Google Gemini API
- Database: Supabase
- Deployment: Vercel
- Node.js 18+ (LTS recommended)
- npm or yarn
- Git
- Clone the repository
git clone https://github.com/yourusername/safeguard-nusantara.git
cd safeguard-nusantara- Install dependencies
npm install- Set up environment variables
cp .env.example .envAdd your API keys to the .env file:
VITE_SUPABASE_URL="your_supabase_url"
VITE_SUPABASE_ANON_KEY="your_supabase_key"
VITE_GEMINI_API_KEY="your_gemini_api_key"
- Start development server
npm run devnpm run buildThe application is deployed at safeguard.mikascend.xyz
- Build the project
npm run build- Install Vercel CLI
npm install -g vercel- Deploy
vercel- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details
Twitter/X - @mikascend