llm-eval

DeepEval

Open-source pytest-style evaluation framework for LLMs and agents

LangWatch

Open-source LLMOps platform for tracing, evaluation and optimization

Maxim AI

End-to-end evaluation, simulation and observability platform for AI agents

Opik

Open-source platform to debug, evaluate and monitor LLM and agent apps

Promptfoo

Open-source evaluation and red-teaming for LLM apps, agents and RAG.