etsi-ai/etsi-watchdog
Real-time data drift detection and monitoring for machine learning pipelines.
This tool helps data scientists and MLOps engineers ensure their machine learning models continue to perform accurately in production. It takes historical model training data and continuously compares it against new, live inference data. The output is real-time alerts and reports indicating when the characteristics of the incoming data have shifted, which can degrade model performance.
Use this if you need to automatically detect and be notified about changes in your live production data that might negatively impact your machine learning model's predictions.
Not ideal if you are looking for a general-purpose anomaly detection tool for non-ML data streams, as its primary focus is on machine learning data drift.
Stars
31
Forks
28
Language
Python
License
BSD-2-Clause
Category
Last pushed
Dec 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/etsi-ai/etsi-watchdog"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
online-ml/river
🌊 Online machine learning in Python
IFCA-Advanced-Computing/frouros
Frouros: an open-source Python library for drift detection in machine learning systems.
NannyML/nannyml
nannyml: post-deployment data science in python
Western-OC2-Lab/AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics
Implementation/Tutorial of using Automated Machine Learning (AutoML) methods for static/batch...
Western-OC2-Lab/PWPAE-Concept-Drift-Detection-and-Adaptation
Data stream analytics: Implement online learning methods to address concept drift and model...