@geonosis/evals
The eval set as a scored CI suite — tasks and compliance-under-pressure prompts through a headless runner, scored from what a runner wrote and never from what the scored process said about itself.
Activity
- Latest release
- 1w ago
- Total releases
- 36
- Cadence
- ~daily
- Last 12 months
- 36
Reach
- Downloads (recent)
- 449
Details
- License
- Apache-2.0
- First release
- Aug 30, 2026
Releases