agent-eval-kit
esm
TypeScript-native eval framework for AI agent workflows. Record-replay, deterministic + LLM graders, trajectory evaluation.
Version 0.1.0 License MIT
Keywords
aiagentevalevaluationtestingllmgraderrecord-replay
INSTALL
TypeScript-native eval framework for AI agent workflows. Record-replay, deterministic + LLM graders, trajectory evaluation.