agentharness agents

3 tagged agentharness, measured the same way as everything else here.

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 3 mods

analyzer

01

archimedes-run/omniHarness

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

6 8d ago A 0 tokens copy · 100% MIT

comparator

02

archimedes-run/omniHarness

Agent

Compare two outputs WITHOUT knowing which skill produced them.

6 8d ago A 0 tokens copy · 100% MIT

grader

03

archimedes-run/omniHarness

Agent

Evaluate expectations against an execution transcript and outputs.

6 8d ago A 0 tokens copy · 100% MIT