# Evidently AI

An open-source framework to evaluate, test and monitor LLMs, RAG apps, AI agents and ML models.

Evidently is an open-source AI evaluation and observability framework. One framework evaluates, tests and monitors LLMs, RAG applications, AI agents and classic ML models. It runs automated evaluations in a pipeline, generates synthetic and adversarial test inputs, and tracks production data drift and data quality. The site lists failure types it targets: hallucinations, edge cases, data and PII leaks, risky outputs and jailbreaks. The framework is open source under Apache 2.0.

Price: Open-source framework (Apache 2.0). Site: https://www.evidentlyai.com/.

Also on the [web page](https://aigovernancetools.fyi/apps/evidently-ai).