← back to the directory
Library / SDK Observability & Evaluation

AgentOps

1Observability 2and 3testing 4for 5AI 6agents

the six Ws · specification

W1 Who

Maintained by AgentOps.

W2 What

Observability, tracing, and testing for AI agents.

W3 Where

A Python SDK sending data to AgentOps or self-hosted.

W4 When

When debugging and monitoring agent runs.

W5 Why

Session replays and analytics built for agents.

W6 With

SDK instrumentation in your agent code.

W7 Watch

Company-maintained; open-source SDK, with a hosted platform (open-core). Traces go to the AgentOps cloud by default unless self-managed.

ObservabilityTestingAgents

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.