Local Model Agent Evaluation

Evaluate local LLMs for agent/coding tasks — BenchLoop harnesses, coding agent selection, tool-calling format matching, and community-tested setups.

theheavenlyd3mon Updated 60 repo stars

File contents

theheavenlyd3mon/hermes-profiles commit e4e73b8422

Frequently asked questions

npx get-skill add theheavenlyd3mon/local-model-agent-evaluation