Anomaly detection refers to the identification of rare events that differ significantly from the normal behavior observed in the data distribution. When the number of variables to analyze is large, it can be difficult to understand why the system has fired an alert without explanation. In this work, we present the prototype of an explainable real-time monitoring and anomaly detection system, on measurements obtained from a data stream. The built system consists of a set of anomaly detection methods combining deeplearning and decision trees as well as an agnostic explainability method. In an unsupervised learning context, we also show how explainability provides insights to validate the system along with feedback from domain experts.