Evaluation Context Protocol proposes a JSON-RPC contract layer for agent evals.

ECP captures agent outputs, tool invocations, and audit context uniformly, with adapters for LangChain, LlamaIndex, CrewAI, and PydanticAI so the same checks run against any of them. arXiv The authors explicitly label it work-in-progress with the method set expected to change. Watch it, don't adopt it.