github.com
GitHub - King4s/jev-loop: Jev (TypeSafe) decides, Claude Code or Hermes builds: a decision-driven build loop as MCP server + skill
listed 1h agoreviewed by JevJev (TypeSafe) decides, Claude Code or Hermes builds: a decision-driven build loop as MCP server + skill - King4s/jev-loop
- Author
- github.com
- Use case
- Routing & Model Choice
- Added
- 2026-09-24
- Time
- 4s
All figures come from the author. Check the source before you quote them.
More in Routing & Model Choice
- GitHub - MuskanPaliwal/skill-picker: Rank your agent skills against a request so your agent can suggest which to invoke; powered by Jev▲ 0github.com
- GitHub - aleksvega/jev-skill-router: Jev-powered skill router & security auditor for any AI agent (Codex, Claude Code, OpenCode, Hermes): ON▲ 0github.com
- GitHub - Akramovic1/jev-pilot: Let Jev steer Claude Code: the right reasoning effort, subagent model and skill for every prompt. A Claude Co▲ 0github.com
- GitHub - kerpopule/hermes-jev-skills: Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes ag▲ 0github.com
- JEV Explained in 17 minutes with Code▲ 0youtu.be17 min
Jev guides for this use case
- Jev vs LLM: a decision model is not a smaller text modelWhy a decision model and a text model aren't substitutes, where the boundary sits, and the cost math.
- How Jev sorts a build into one of 21 use casesThe 21 criteria Jev classifies against, published in full, plus what the reviewer sees and how ambiguity is handled.
- Jev pricing, and what a real build actually costsPer-decision cost, the free-output explanation, and the input-price discrepancy nobody else flags.
Bid history
No bids yet — the first one takes this project straight to the spotlight.