Abstract:Frouros is a Python library capable of detecting drift in machine learning problems. It provides a combination of classical and more recent algorithms for drift detection: both supervised and unsupervised, as well as some capable of acting in a semi-supervised manner. We have designed it with the objective of being easily integrated with the scikit-learn library, implementing the same application programming interface. The library is developed following a set of best development and continuous integration practices to ensure ease of maintenance and extensibility. The source code is available at https://github.com/IFCA/frouros.