{"slug": "show-hn-a-lightweight-model-monitor-for-scikit-learn-and-keras", "title": "Show HN: A lightweight model monitor for scikit-learn and Keras", "summary": "Canary ML, a new open-source Python library, provides lightweight drift and anomaly detection for production machine learning models built with scikit-learn, Keras, and TensorFlow. The tool wraps existing models to monitor predictions, detect data drift, and serve a dashboard, aiming to help developers maintain model performance in production.", "body_md": "Drift and anomaly detection for production ML models. Cutting-edge performance in a wrapper, for free.\n\npip install canary-ml\n\nKeras/TensorFlow: pip install canary-ml[keras]\n\npip install canary-ml[keras]\n\n``` python\nfrom canary_ml import ModelMonitor\n\nmonitor = ModelMonitor(\n    model=your_model,\n    reference_data=X_train,\n    alert_threshold=0.2,\n    log_path=\"./canary_logs\"\n)\n\n# drop-in replacement — monitoring is a side effect\npredictions = monitor.predict(X_new)\n\nreport = monitor.get_report()\nprint(report.psi_score, report.drift_detected, report.anomaly_rate)\n# 0.41  True  0.032\n\nmonitor.serve_dashboard(port=8501)\n```\n\n", "url": "https://wpnews.pro/news/show-hn-a-lightweight-model-monitor-for-scikit-learn-and-keras", "canonical_source": "https://aitor1717.github.io/canary-ml/", "published_at": "2026-07-14 15:39:43+00:00", "updated_at": "2026-07-14 15:47:53.806983+00:00", "lang": "en", "topics": ["machine-learning", "developer-tools", "ai-tools", "mlops"], "entities": ["Canary ML", "scikit-learn", "Keras", "TensorFlow"], "alternates": {"html": "https://wpnews.pro/news/show-hn-a-lightweight-model-monitor-for-scikit-learn-and-keras", "markdown": "https://wpnews.pro/news/show-hn-a-lightweight-model-monitor-for-scikit-learn-and-keras.md", "text": "https://wpnews.pro/news/show-hn-a-lightweight-model-monitor-for-scikit-learn-and-keras.txt", "jsonld": "https://wpnews.pro/news/show-hn-a-lightweight-model-monitor-for-scikit-learn-and-keras.jsonld"}}