# kerpopule/hermes-jev-skills > A set of eight SKILL.md files and a CLI that wires the Jev decision model into Hermes, Claude Code and Codex agents for model routing, memory filtering, skill selection and GUI actions. - Magnitude: 1.2 out of 10 — Cooling - Stars: 1,015 total · +0 stars on 2026-10-05 (UTC), ≈ 7 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: MIT · Created: 2026-09-18 · Last push: 2026-10-02 - GitHub: https://github.com/kerpopule/hermes-jev-skills · Page: https://gitnova.dev/en/r/kerpopule/hermes-jev-skills ## Useful for - Run model routing in shadow mode to log decisions for a day without switching - Filter 60 retrieved memory passages before sending them to the expensive model - Pick the right skill out of 377 installed ones for a single agent turn ## Why it’s here - 0 stars so far today, about 7 expected by the end of the day. - The repository is 17 days old and already has 1,015 stars. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 101 - Issues and pull requests: 33 - Watchers: 1 - Average over the last week: 18 per day - Usual pace: 52 per day - Latest release: v0.22.1 (2026-10-02) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-18 … 2026-11-16: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 09-22 5.1, 09-23 5.5, 09-24 4.4, 09-25 4.0, 09-26 3.4, 09-27 2.0, 09-28 2.3, 09-29 2.1, 09-30 2.2, 10-01 2.6, 10-02 2.7, 10-03 1.9, 10-04 1.3, 10-05 1.2 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-05 00:17 UTC, updated every 30 minutes.