All open source
Open SourceAnalytics6k

Evidently

Open-source evaluation and monitoring for ML and LLM systems.

Evidently is an open-source Python library for evaluating, testing, and monitoring data and AI systems, spanning classic ML and LLM use cases. It offers 100+ built-in metrics and tests for data drift, model quality, and LLM output quality, rendered as interactive reports or test suites. It can run as ad-hoc checks in a notebook or as scheduled monitoring with an optional dashboard.

Repository

evidentlyai/evidently

Language

Python

What you'd build with it

  • Detect data and prediction drift on a deployed ML model over time
  • Evaluate LLM outputs for quality, toxicity, and correctness with prebuilt metrics
  • Build automated test suites and monitoring dashboards for production AI pipelines

Tags

ml-monitoringdrift-detectionevalsobservability