"It ain't much, but it's honest work"

GitHire - AI Coding Interview Platform

AI interviewer that generates coding questions, executes Python code in isolated E2B sandboxes, and provides automated feedback.

Features

• AI-Generated Questions - LLM generates coding challenges
• Safe Code Execution - E2B sandboxes isolate user code
• Automated Scoring - LLM evaluates correctness and code quality
• Modern UI - Dark mode, Monaco editor, real-time feedback

Tech Stack

Backend:

• FastAPI - Modern Python web framework
• LangChain - LLM orchestration
• E2B Code Interpreter - Secure sandboxed execution
• Pydantic - Data validation

Frontend:

• Next.js 14 - React framework
• TypeScript - Type safety
• Tailwind CSS - Styling
• Monaco Editor - Code editing
• React Hot Toast - Notifications

Quick Start

Prerequisites

• Python 3.11+
• Node.js 18+
• OpenAI API key
• E2B API key

Environment Setup

# Copy environment template
cp .env.example .env

# Add your API keys to .env
OPENAI_API_KEY=your_openai_api_key
E2B_API_KEY=your_e2b_api_key

Running Locally

Backend:

cd backend
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt
uvicorn app.main:app --reload --port 8000

Frontend:

cd frontend
npm install
npm run dev

Access the application at http://localhost:3000

Docker Deployment

# Build and start all services
docker-compose up --build

# Run in background
docker-compose up -d --build

# Stop services
docker-compose down

See DEPLOYMENT.md for detailed instructions.

Project Structure

githire-e2b-cookbook/
├── backend/
│   ├── app/
│   │   ├── api/          # API routes
│   │   ├── services/     # Business logic (E2B, LLM)
│   │   ├── models/       # Pydantic schemas
│   │   ├── utils/        # Logging, helpers
│   │   └── main.py       # FastAPI application
│   ├── Dockerfile
│   └── requirements.txt
├── frontend/
│   ├── src/
│   │   ├── app/          # Next.js pages
│   │   └── components/   # React components
│   ├── Dockerfile
│   └── package.json
├── docker-compose.yml
├── DEPLOYMENT.md         # Docker deployment guide
├── E2B.md               # E2B technical documentation
└── .env.example

API Endpoints

• POST /api/start - Start new interview session
• POST /api/submit - Submit code for evaluation
• GET /api/session/{id} - Get session data
• GET /health - Health check
• GET /docs - API documentation (Swagger)

E2B Sandboxing

E2B runs user code in isolated Docker containers:

• Each execution gets a fresh container
• No access to host system or secrets
• Automatic cleanup after execution
• 30s timeout and output limits

Configuration

Environment variables (.env):

# Required
OPENAI_API_KEY=           # OpenAI API key
E2B_API_KEY=              # E2B API key

# Optional
LLM_MODEL=gpt-4o-mini     # OpenAI model (default: gpt-4o-mini)
ENVIRONMENT=development    # Environment mode
LOG_LEVEL=INFO            # Logging level
FRONTEND_URL=http://localhost:3000
NEXT_PUBLIC_API_URL=http://localhost:8000

Development

Backend:

# Run with auto-reload
uvicorn app.main:app --reload --port 8000

# Format code
black app/

Frontend:

# Development server
npm run dev

# Build for production
npm run build

# Start production server
npm start

Production Deployment

Recommended for production:

• Use Docker deployment
• Set ENVIRONMENT=production
• Configure LOG_LEVEL=WARNING
• Implement rate limiting
• Add session persistence (Redis)
• Set up monitoring and alerts

License

MIT