All projects

typed_evals

TrustifAI/typed_evals

Fast, typed, calibrated evaluations for LLM and agent outputs, powered by Jev — with simple, framework-agnostic Python APIs

Research & evaluationPython
Stars
9
Forks
1

Review source

View cited source

Topics

jevaiai-agentscrewaievalsevaluationevaluation-frameworkevaluation-metrics