Rank #859 · on radar since 2026-07-03

eval-harness

Behavior-regression testing for LLM agents. 4-class attribution, 6-field FAIL schema, $-cost gating, flaky detection. Bash + jq. Works with opencode today, runner-pluggable.

Why it's ranked

Every score decomposes into published factors — the same math for every tool, paid or not. Read the methodology →