Midas is a modern financial management platform that combines real-time transaction tracking with AI-powered insights. Using advanced data visualization and a conversational AI interface, Midas helps users understand their spending patterns and make better financial decisions.
- Frontend: Next.js 15, Shadcn UI, Tailwind CSS, Three.js, Radix UI, Chart.js
- Backend: Convex, Flask, Next.js
- AI: Gemini
- Authentication: Clerk
- Banking Integration: Plaid
- Machine Learning: PyTorch
- Node.js (Latest LTS version)
- npm or yarn
- A Convex account
- A Clerk account
- A Plaid account (for banking integration)
# Clone the repository
git clone https://github.com/ArslanKamchybekov/midas.git
# Navigate to the project directory
cd uncommonhacks
# Install dependencies
npm install
# Set up environment variables
cp .env.local# Start the development server
npm run dev
# Start Convex development server
npx convex dev# Build the application
npm run build
# Start the production server
npm start- Real-time transaction tracking
- Dynamic spending analytics
- Category-based expense breakdown
- Interactive charts and graphs
- Natural language financial queries
- Personalized financial insights
- Budget recommendations
- Anomaly detection in spending patterns
- Automatic transaction categorization
- Custom budget settings
- Weekly budget tracking
- Bi-weekly budget tracking
- Monthly budget tracking
- Real-time transaction updates
- Bar charts for category spending
- Pie charts for expense distribution
- Line charts for spending trends
- Anomaly detection visualization
Simply chat with Midas using natural language. Example queries:
- "How are my finances looking?"
- "Show me my spending by category"
- "What's my biggest expense this month?"
- "Am I staying within my budget?"
- "Any unusual spending patterns?"
- Secure authentication via Clerk
- Encrypted banking connections through Plaid
- Protected API endpoints
- Secure data storage with Convex
- Import transactions via CSV
- Connect bank accounts through Plaid
- Real-time transaction syncing
- Automated categorization
Contributions are welcome! Please feel free to submit a Pull Request.
