⬢github Python · 850 ★ +3 since we first saw it · pushed 2 h ago · MIT
kerpopule/hermes-jev-skills
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
A set of Python-based agent 'skills' that offload small, frequent decisions from expensive frontier LLMs to Jev, TypeSafe's decision-only model. It handles model routing, memory filtering, prompt-injection screening, transcript compaction, skill selection, message triage, mailbox sorting, and computer/browser use. Skills ship as plain SKILL.md files, so they work with Hermes agents, Claude Code, Codex, or anything that reads skill files.
Why now: Recently created and climbing the most-starred new repos list, with freshly published evaluation scorecards showing strong injection-detection and recall results.
Who it is for: Developers building or running coding agents who want to cut token costs and latency by routing trivial decisions to a cheap decision model.
Stars over our 15 snapshots: 847 to 850, since 1 h ago.
Where people talked about it
- ⬢github new repos, most starred 9 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/kerpopule/hermes-jev-skills