vcruz305

2 mods across 1 repository, 12 stars between them.

hermes-bench

01

vcruz305/hermes-agentic-bench

Skill Claude CodeCodex

Set up and run the hermes-agentic-bench agentic test battery (simulated OpenAI-endpoint battery and/or real Hermes CLI battery) against one or more local models, then generate a comparison report.

12 18d ago A 48 tokens original MIT

hermes-bench

02

vcruz305/hermes-agentic-bench

Skill Claude CodeCodex

Run hermes-agentic-bench's agentic tool-use test battery against a model and report results.

12 18d ago A 26 tokens original MIT