agentevals-evaluator-sdk
Lightweight SDK for building custom agentevals evaluators
An evaluator is a standalone program that scores agent traces. It reads EvalInput JSON from stdin and writes EvalResult JSON to stdout. This SDK provides the Python types and a @evaluator decorator that handles all the plumbing.
⚡ How to use agentevals-evaluator-sdk
Indexed from PyPI. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/agentevals-evaluator-sdkCapabilities
Do you own agentevals-evaluator-sdk?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.