An AI-powered essay grading application built for PatriotHacks 2026. Save time and ensure consistency by automatically grading student essays against your custom rubrics.

• AI-Powered Grading: Leverages Google Gemini to evaluate essays against your rubric
• Multi-Format Support: Accepts PDF, TXT, PNG, JPG, and more
• Detailed Feedback: Provides criterion-by-criterion scores and feedback
• Batch Processing: Grade multiple essays at once
• Fast & Accurate: Get results in seconds, not hours

• Frontend: SvelteKit, TypeScript, Tailwind CSS
• Backend: Python FastAPI
• AI: Google Gemini 3 Flash (2.0 flash for fallback)

• Bun for the frontend
• Python 3.12+ for the backend
• Google Gemini API Key

1. Clone the repository

git clone <repository-url>
cd patriothacks2026

2. Set up the backend

cd backend
cp .env.example .env  # or create .env manually
# Add your GEMINI_API_KEY to .env
uv sync

3. Set up the frontend

cd frontend
bun install

Backend (Terminal 1):

cd backend
uv run fastapi dev main.py

The API will be available at http://localhost:8000

Frontend (Terminal 2):

cd frontend
bun run dev

The app will be available at http://localhost:5173

1. Navigate to the grader page
2. Upload your grading rubric (PDF, Image or TXT)
3. Upload student essays (single or multiple)
4. Add optional instructor notes for context
5. Click "Grade" and receive instant feedback

patriothacks2026/
├── frontend/          # SvelteKit frontend
│   ├── src/
│   │   ├── lib/      # Shared components
│   │   └── routes/   # App routes
│   └── package.json
└── backend/          # FastAPI backend
    ├── main.py       # API entry point
    ├── services/     # Business logic
    └── pyproject.toml

MIT