AgentPulse, drift investigation for multi vs Evaluation Context Protocol (ECP)

Open-source drift investigation for multi-agent systems: which agent drifted, where it originated, and what to check next.

ECP is a vendor-neutral JSON-RPC protocol for grading agent outputs, tool calls, and audit context across frameworks, models, and CI systems.

About AgentPulse, drift investigation for multi

Open-source drift investigation for multi-agent systems: which agent drifted, where it originated, and what to check next. What did change is the payload it receives from writer, starting at the same run. So critic is probably downstream damage, not the source. After the change, writer responses run ~180% longer and drop the section structure critic expects, earlier payloads were structured summaries, newer ones read as prose. If restoring the format fixes critic, make the fix in writer.

About Evaluation Context Protocol (ECP)

ECP is a vendor-neutral JSON-RPC protocol for grading agent outputs, tool calls, and audit context across frameworks, models, and CI systems. ECP gives evaluators a common way to inspect what an agent returned, what tools it used, and what audit evidence it exposed, independent of the framework that built the agent or the platform that runs the test. tool_calls Did the agent call the required tool with the right arguments?. ecp run --manifest Can this run in CI and fail a build?.