Top/llm-evaluation

The most inspiring discoveries in llm evaluation

github.com

Promptfoo is a CLI tool for evaluating and securing LLM applications through automated testing and red teaming.

cici-cdcicdclaudeevaluation

flux

github.com

Langfuse is an open source platform for LLM observability and management, enabling teams to develop and debug AI applications efficiently.

analyticsautogenevaluationlangchainlarge-language-models

flux

github.com

Agenta is an open-source platform for building reliable LLM applications with integrated management, evaluation, and observability tools.

agentsevaluationllmllm-as-a-judgellm-evaluation

flux