🎬 Glitch x Google Hackathon: AI-Powered Video Editor

An intelligent, agentic video editing platform combining a modern Next.js frontend with a FastAPI backend powered by Google Gemini AI. The system intelligently routes video processing tasks across multiple AI providers based on semantic user prompts.

✨ Features

• 🤖 AI-Driven Decision Making: Gemini-powered agent analyzes user prompts and intelligently routes tasks
• 🎯 Multi-Provider Support: Dynamically adapts between Veo, Nanobanana, and Lyria APIs for optimal results
• ✂️ Interactive Video Editor: Real-time timeline editing with live preview and media panel
• 🏗️ Modular Architecture: Clean separation between frontend, backend, and AI adapters
• 💬 Conversational History: Track and retrieve session-based AI interactions
• 🔄 Hot-Reload Development: Next.js dev server + FastAPI auto-reload for rapid iteration

🛠️ Tech Stack

Backend

• Framework: FastAPI
• Language: Python 3.13+
• AI: Google Gemini API
• Validation: Pydantic
• Server: Uvicorn
• Cache: Redis
• Async: Python asyncio

Frontend

• Framework: Next.js 16
• UI Library: React 19
• Styling: Tailwind CSS v4
• Language: TypeScript
• Icons: FontAwesome
• Linting: ESLint

📂 Project Structure

glitch-google-hackathon_26/
├── agentic-monorepo-backend/
│   ├── backend/
│   │   ├── main.py                    # FastAPI app entry
│   │   ├── agent/
│   │   │   └── gemini_agent.py        # Gemini decision logic
│   │   ├── router/
│   │   │   └── model_router.py        # Smart model routing
│   │   ├── adapters/
│   │   │   ├── veo/
│   │   │   ├── nanobanana/
│   │   │   └── lyria/
│   │   ├── schemas/
│   │   │   ├── agent_output.py
│   │   │   └── prompt_request.py
│   │   └── utils/
│   │       ├── config.py
│   │       ├── helpers.py
│   │       └── system_prompt.txt
│   └── requirements.txt
├── frontend/
│   ├── src/
│   │   ├── app/
│   │   │   ├── page.tsx               # Main entry
│   │   │   ├── layout.tsx
│   │   │   └── editor/
│   │   └── components/
│   │       ├── Editor.tsx             # Frame editor
│   │       ├── Timeline.tsx           # Keyframe timeline
│   │       ├── MediaPanel.tsx         # Asset management
│   │       ├── PreviewArea.tsx        # Live preview
│   │       ├── AiAssistant.tsx        # Prompt UI
│   │       └── ExportModal.tsx        # Output export
│   ├── package.json
│   └── tsconfig.json
└── README.md

🚀 Quick Start

Prerequisites

• Node.js >= 20 (for frontend)
• Python >= 3.13 (for backend)
• pip or npm (package managers)

Backend Setup

From agentic-monorepo-backend/:

# Create virtual environment
python3 -m venv .venv

# Activate venv
source .venv/bin/activate        # macOS/Linux
# or
.venv\Scripts\activate           # Windows

# Upgrade pip
python -m pip install --upgrade pip

# Install dependencies
python -m pip install -r requirements.txt

Environment Variables

Create a .env file in agentic-monorepo-backend/:

GEMINI_API_KEY=your_gemini_api_key_here
REDIS_URL=redis://username:password@host:port

Run Backend

cd agentic-monorepo-backend
source .venv/bin/activate
python -m uvicorn backend.main:app --reload --host 127.0.0.1 --port 8000

Expected Output:

INFO:     Will watch for changes in these directories: ['.../agentic-monorepo-backend']
INFO:     Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
INFO:     Application startup complete.

Access:

• API: http://localhost:8000
• Docs: http://localhost:8000/docs (Swagger UI)

---

Frontend Setup

From frontend/:

# Install dependencies
npm install

# Run development server
npm run dev

Expected Output:

> next dev
- ready started server on 0.0.0.0:3000, url: http://localhost:3000
- event compiled client and server successfully

Access:

• UI: http://localhost:3000

---

📡 API Reference

POST /prompt - Process User Prompt

Submit a video editing prompt for AI analysis and execution.

Request:

curl -X POST "http://localhost:8000/prompt" \
  -H "Content-Type: application/json" \
  -d '{
    "user_prompt": "Generate a 30-second promo video with upbeat music",
    "session_id": "optional-session-uuid"
  }'

Response:

{
  "session_id": "550e8400-e29b-41d4-a716-446655440000",
  "decision": {
    "model": "veo",
    "reasoning": "Veo is best for video generation tasks",
    "parameters": {...}
  },
  "output": {
    "status": "success",
    "result": {...}
  }
}

GET /conversations/{session_id} - Retrieve Session History

Fetch all conversation messages for a session.

Request:

curl "http://localhost:8000/conversations/550e8400-e29b-41d4-a716-446655440000"

Response:

{
  "session_id": "550e8400-e29b-41d4-a716-446655440000",
  "conversations": [
    {
      "role": "user",
      "content": "Generate a video",
      "timestamp": "2026-03-28T10:30:00Z"
    },
    {
      "role": "assistant",
      "content": "I'll use Veo for this task...",
      "timestamp": "2026-03-28T10:30:05Z"
    }
  ]
}

---

🛠️ Development

Backend Development

cd agentic-monorepo-backend
source .venv/bin/activate

# Run with auto-reload
python -m uvicorn backend.main:app --reload

# Run tests (if available)
pytest

# Code formatting
black backend/

# Type checking
mypy backend/

Frontend Development

cd frontend

# Start dev server with hot-reload
npm run dev

# Build for production
npm run build

# Start production server
npm start

# Lint code
npm run lint

🚢 Deployment

Docker (Optional)

Backend Dockerfile:

FROM python:3.13-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8000"]

Frontend Dockerfile:

FROM node:20-alpine
WORKDIR /app
COPY package*.json .
RUN npm ci
COPY . .
RUN npm run build
CMD ["npm", "start"]

---

📝 Environment Variables Reference

Backend (.env)

Variable	Description	Example
GEMINI_API_KEY	Google Gemini API key	AIza...xyz
REDIS_URL	Redis connection string	redis://user:pass@host:6379

Frontend

No environment variables required by default. API calls default to http://localhost:8000.

---

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push branch (git push origin feature/amazing-feature)
5. Open a Pull Request

---

📄 License

This project is part of the Glitch x Google Hackathon 2026. All rights reserved.

---

👥 Team

• Backend: FastAPI + Gemini Agent Architecture
• Frontend: Next.js Video Editor UI
• AI Integration: Multi-provider routing (Veo, Nanobanana, Lyria)

---