建议: Guardrails Validators 的 EvalPort 适配器 (可移植的评估测试用例 + 结果)

Hi Guardrails team — I maintain EvalPort (Apache 2.0), an open interchange format for portable LLM evaluation test cases, graders, suites, and results as plain JSON. It already has 14 standalone framework adapters (AutoGen, CrewAI, Ragas, LangSmith, Braintrust, MLflow, Opik, Arize Phoenix, W&B Weave, UpTrain, Langfuse, Giskard, LlamaIndex, Patronus AI) and one merged upstream integration (Inspect AI).