AegisOps Core

AegisOps Core is a production-style MVP for predictive maintenance and mechanical anomaly detection. It simulates equipment telemetry, runs rule-based and ML-based (Isolation Forest) anomaly detection layers, and provides a clean dashboard.

Architecture

• Backend: FastAPI, SQLite, scikit-learn. Located in /backend.
• Frontend: Next.js, Tailwind CSS, Recharts. Located in /frontend.
• Infrastructure: docker-compose.yml.

Run with Docker (Recommended)

You can run the full stack effortlessly with Docker:

docker-compose up --build

• Frontend: http://localhost:3000
• Backend API Docs: http://localhost:8000/docs

Note: On first run, you might want to call POST http://localhost:8000/api/seed-data to populate data if the initialization script didn't run automatically, but seeding logic is available!

Screenshots

(Add screenshots here)

Future Improvements

1. Replace SQLite with PostgreSQL/TimescaleDB for production-scale time-series data.
2. Implement WebSocket connections instead of short-polling for real-time telemetry streaming.
3. Add User Authentication (JWT) and RBAC for operator vs admin roles.