IFCA-Advanced-Computing/frouros

Frouros: an open-source Python library for drift detection in machine learning systems.

58
/ 100
Established

When machine learning models are deployed, their performance can degrade over time as the real-world data they encounter changes. This tool helps machine learning engineers and MLOps specialists automatically detect when these changes, known as 'drift,' occur in either the input data or the relationship between inputs and outputs. It takes in streaming model predictions and actual data, then flags when the model's environment has shifted.

252 stars. Available on PyPI.

Use this if you need to continuously monitor your deployed machine learning models and be alerted when the underlying data patterns or concept definitions change, impacting model reliability.

Not ideal if you are looking for a tool to retrain or update your models automatically after drift is detected, as it focuses solely on detection.

machine-learning-operations model-monitoring data-quality predictive-maintenance fraud-detection
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

252

Forks

19

Language

Python

License

BSD-3-Clause

Last pushed

Mar 01, 2026

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IFCA-Advanced-Computing/frouros"

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