Evidently AI

Evidently is an open-source framework to evaluate, test and monitor AI-powered apps. 📚 100+ built-in checks, from classification to RAG. 🚦 Both offline evals and live monitoring. 🛠 Easily add custom metrics and LLM judges.

Evidently AI is an open-source framework designed to evaluate, test, and monitor AI-powered applications, particularly those using large language models (LLMs). It offers over 100 built-in metrics for tasks like classification and retrieval-augmented generation (RAG), supporting both offline evaluations and live monitoring. Users can easily integrate custom metrics and LLM-based evaluations, making it highly adaptable. Trusted by thousands of companies, Evidently helps detect issues like data drift, hallucinations, and risky outputs, ensuring robust model performance. Its intuitive interface, detailed documentation, and flexibility make it a go-to tool for MLOps teams aiming to maintain AI reliability and transparency in production environments.