F1 Race Engineer AI is a real-time analytics platform designed to support Formula 1 race engineers. It creates an AI agent per driver that learns each driver's "normal" driving behavior after a few laps, detects anomalies, and correlates them with team radio commands transcribed via ElevenLabs Speech-to-Text.

Goal: Decrypt team codewords — e.g., identifying that "full speed ahead" consistently triggers a speed increase.

• 🧠 AI-Powered Anomaly Detection: Machine learning algorithms detect unusual driving patterns
• 🎙️ Real-Time Radio Transcription: ElevenLabs Speech-to-Text for team communications
• 📊 Live Telemetry Visualization: Real-time F1 data with galaxy-themed UI
• 🔍 Codeword Analysis: Correlate radio phrases with driving behavior changes
• 📈 Performance Analytics: Driver summaries and trend analysis
• ☁️ Cloud-Native Architecture: Scalable Kubernetes deployment
• 🌌 Immersive UI: Celestial-themed dashboard with real-time updates

• Driver agents: Learn per-driver patterns and detect anomalies.
• Speech correlation: Align driving anomalies with radio phrases.
• ElevenLabs: Converts open radio into timestamped transcripts.
• Gemini API: Generates live driver summaries every few laps.
• React + Tailwind UI: Visualizes real-time data with a celestial theme.

flowchart LR
  subgraph Track
    T[Telemetry Data] -->|Kafka Topic: telemetry| K[(MSK/Kafka)]
    R[Team Radio Audio] -->|ElevenLabs STT| TXT[Transcripts]
    TXT -->|Kafka Topic: radio| K
  end

  K --> SPARK[Apache Spark Streaming]
  SPARK -->|Anomaly & Phrase Stats| S3[(S3 or DigitalOcean Spaces)]
  SPARK --> API[FastAPI Gateway]
  API --> UI[React + Tailwind UI]
  SPARK --> SUM[Gemini Summaries]

{
  "ts": "2025-10-18T18:30:01.235Z",
  "driver_id": "DRIVER_A",
  "lap": 7,
  "distance_m": 3612.4,
  "sector": 2,
  "track_x": 0.83,
  "speed_kph": 281.7,
  "throttle_pct": 0.96,
  "brake_pct": 0.02,
  "gear": 7
}

{
  "ts": "2025-10-18T18:30:01.120Z",
  "team": "TEAM_X",
  "driver_id": "DRIVER_A",
  "text": "Full speed ahead"
}

{
  "ts": "2025-10-18T18:30:01.400Z",
  "driver_id": "DRIVER_A",
  "feature": "speed_kph",
  "score": 3.2,
  "value": 281.7,
  "baseline": 270.4
}

{
  "phrase": "full speed ahead",
  "driver_id": "DRIVER_A",
  "window_s": 5,
  "count": 12,
  "p(anomaly|phrase)": 0.67,
  "top_features": ["speed_kph", "throttle_pct"]
}

1. Simulator generates telemetry + radio streams.
2. Kafka handles telemetry/radio topics.
3. Spark Streaming detects anomalies and correlations.
4. Gemini produces live summaries.
5. Gateway relays data to the React UI via WebSocket.

• Docker & Docker Compose
• Node.js 18+ (for local development)
• Python 3.11+ (for local development)
• kubectl (for Kubernetes deployment)
• Terraform (for infrastructure deployment)

1. Clone the repository

   git clone https://github.com/yourusername/f1-race-engineer-ai.git
   cd f1-race-engineer-ai

2. Set up environment variables

   cp env.example .env
   # Edit .env with your API keys

3. Deploy locally

   ./scripts/deploy.sh local

4. Access the application

   • Frontend: http://localhost:3000
   • Backend API: http://localhost:8000
   • Kafka: localhost:9092

# Deploy AWS infrastructure
./scripts/deploy.sh infrastructure aws

# Deploy to Kubernetes
./scripts/deploy.sh k8s

# Deploy DigitalOcean infrastructure
./scripts/deploy.sh infrastructure digitalocean

# Deploy to Kubernetes
./scripts/deploy.sh k8s

• S3, Glue, Athena, MSK, EMR Serverless, Secrets Manager
• Use infra/terraform to deploy

cd infra/terraform
terraform init && terraform apply -auto-approve

• Creates VPC, Spaces, DOKS cluster, Kafka (Bitnami Helm), and Ingress

cd infra/doks-terraform
terraform init && terraform apply -auto-approve

Fetch kubeconfig:

doctl kubernetes cluster kubeconfig save $(terraform output -raw doks_name)

Deploy app:

kubectl apply -f k8s/

• Navy blue #0b1b3b background with white galaxy glow.
• Real-time driver panels with speed/throttle/brake gauges.
• Live "codeword" probability indicators.

# Install all dependencies
npm run install-all

# Start development servers
npm run dev

# Run telemetry simulator
npm run simulator

# Build Docker images
./scripts/deploy.sh build

# Deploy to Kubernetes
./scripts/deploy.sh k8s

# Clean up resources
./scripts/deploy.sh cleanup

1. ElevenLabs: Sign up at elevenlabs.io and get your API key
2. Google Gemini: Get your API key from Google AI Studio

• Integrate LSTM autoencoders for anomaly detection.
• Add real radio feeds from public APIs.
• Build driver style profiling over races.
• Integrate real telemetry APIs for Formula Student teams.
• Add machine learning model training pipeline
• Implement real-time video analysis for driver behavior
• Add predictive analytics for race outcomes

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

MIT License © 2025 Sahishnu "Sahi" Sagiraju
Use freely for educational & research purposes.

• Formula 1 teams for inspiration
• ElevenLabs for speech-to-text technology
• Google for Gemini AI capabilities
• The open-source community for amazing tools

For questions, issues, or contributions, please:

• Open an issue on GitHub
• Contact: your-email@example.com
• Follow on Twitter: @yourusername