sintel-dev/Orion

Unsupervised time series anomaly detection library

58
/ 100
Established

This tool helps operations engineers, data scientists, or anyone monitoring systems or processes to automatically find unusual patterns in their time-based data. You feed it a stream of observations, like server metrics or sensor readings, and it tells you when and where abnormal behavior occurred, helping you quickly spot issues. It's designed for someone who needs to identify unexpected events without manually sifting through mountains of data.

1,343 stars.

Use this if you have continuous streams of data over time and need to automatically identify unusual spikes, drops, or changes that could indicate problems or interesting events.

Not ideal if your data isn't time-series based, or if you need to detect anomalies in categorical data or static datasets without a temporal component.

operations-monitoring system-health sensor-data-analysis fraud-detection performance-monitoring
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,343

Forks

195

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sintel-dev/Orion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.