Agent Eval Harness
HarnessFreeBuild a real eval suite for an agent or prompt: cases, graders, a baseline, and a regression gate
v1.0.0MIT1 download
npx openagents-cli add openagents/eval-harness --runtime claude-code| Path | Size |
|---|---|
| grading.md | 1.7 KB |
| HARNESS.md | 3.2 KB |
| openagent.yaml | 792 B |
| README.md | 1.2 KB |
templates/1 file
| Path | Size |
|---|---|
| cases.jsonl | 1.1 KB |