ML/LLM Observability Framework
7.4k 2026-04-14

evidentlyai/evidently

An open-source Python library for evaluating, testing, and monitoring ML and LLM systems across experiments and production environments.

Core Features

Comprehensive evaluation, testing, and monitoring for ML and LLM systems.
Offers 100+ built-in metrics for data drift, model performance, and LLM-specific evaluations.
Provides interactive Reports for analysis, Test Suites for validation, and a Monitoring Dashboard for live observability.
Supports both offline evaluations and continuous production monitoring for tabular and text data.

Quick Start

pip install evidently

Detailed Introduction

Evidently is a powerful open-source Python library designed to bring transparency and reliability to AI-powered systems. It enables data scientists and MLOps engineers to evaluate, test, and continuously monitor machine learning and large language model systems, from initial experiments to full production deployment. With over 100 built-in metrics, it addresses critical issues like data drift, model performance degradation, and LLM-specific challenges, ensuring the robustness and fairness of AI applications.

OSS Alternative

Explore the best open source alternatives to commercial software.

© 2026 OSS Alternative. hotgithub.com - All rights reserved.