User repository on GitHub
Jev decision sidekick for Hermes Agent — TypeSafe and Cloudflare, explicit tools and official skill
- Forks
- 2
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
Hermes Jev — ourines
A native Hermes Agent tool plugin - not a chat-model provider - where Jev supplies bounded semantic judgments and an explicit model recommendation while the main agent keeps planning, generation, execution and approvals. Backends: TypeSafe, Cloudflare and OpenRouter.
- Stars
- 2
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- ourines
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Hermes Jev — keeltrace.
Used inJev for Software & DevTools
- Languages
- Python
- Platforms
- CLICloudflareOpenRouter
- Capabilities
- Open sourceRequires API key
Highlights
- A native tool plugin, not a chat-model provider: Jev gives bounded semantic judgments and a model recommendation while Hermes keeps planning and approvals.
- Three explicit backends: TypeSafe (jev-latest), Cloudflare AI (typesafe/jev) and OpenRouter (typesafe/jev-1.13), each with its own credential and endpoint.
- OpenRouter's alpha endpoint rejects the jev-latest alias with HTTP 400, so that backend pins the versioned model id and lets --model override it.
- Setup uses hidden terminal input, has no --api-key argument, and makes one tiny live evaluation before saving credentials; failed validation saves nothing.
- v0.1.2 is a prerelease: a live Cloudflare Chinese smoke test passed with jev-1.13.0, while TypeSafe access and real-workload accuracy remain unverified.
Quickstart
bash
hermes plugins install ourines/hermes-jev --enable
hermes jev setup --backend typesafeWatch out
Grounded on the truncated README and GitHub metadata reviewed 2026-10-15; the README cuts off mid-sentence in the status command examples. It is a community/custom source rather than a Hermes catalog entry, developed against Hermes 0.21.3, and the README recommends reviewing the source and pinning a release commit SHA.
Questions about this entry
Short answers drawn from the linked project or page.
A native tool plugin for the Hermes Agent: Jev supplies bounded semantic judgments and an explicit model recommendation while the main Hermes agent keeps planning, generation, tool execution and responsibility for approvals.
Three, selected explicitly: TypeSafe official with jev-latest, Cloudflare AI with typesafe/jev, and OpenRouter with typesafe/jev-1.13. There is no cross-provider fallback or automatic retries.
Install with `hermes plugins install ourines/hermes-jev --enable`, then run `hermes jev setup --backend typesafe` (or cloudflare/openrouter). A reproducible install can add --ref with a release commit SHA.
It asks via hidden terminal input and refuses non-interactive entry; there is deliberately no --api-key argument. One tiny live evaluation runs before credentials are saved, and a failed validation saves nothing.
No. The README describes it as a tool plugin, not a chat-model provider; the main model is untouched, and a backend switch leaves the previous credential available but inactive.
OpenRouter's alpha endpoint rejects the jev-latest alias with HTTP 400, so the backend defaults to typesafe/jev-1.13 and lets --model override it; results preserve the actual model ID returned.
v0.1.2 is a prerelease: a live Cloudflare Chinese smoke test passed with jev-1.13.0, while direct TypeSafe access and real-workload accuracy remain unverified. It was developed against Hermes 0.21.3.
More Jev resources like this
An independent agent skill that walks a coding agent through designing a bounded Jev decision layer: contract, criteria, error behavior, fallback, and evaluation plan first, then scaffolding through TypeSafe or OpenRouter.
Jev Agents & MCP#community#catalog-import#logicrw
Community
grandamenium/jev-anythingPython
grandamenium/jev-anythingPythonA Claude Code plugin and zero-dependency Python CLI that judges items in bulk with calibrated Jev answers, resolves the confident ends in code, and sends only the uncertain band to Claude or a human.
Jev Agents & MCP#community#catalog-import#logicrw
Claude Code plugin that asks Jev a few typed questions before every turn and sets reasoning effort, subagent model and effort, strategy, and the skill a prompt needs; you keep Opus for the conversation.
Jev Agents & MCP#community#catalog-import#logicrw
Community
akramovic1/jev-pilotTypeScript
akramovic1/jev-pilotTypeScriptA Claude Code plugin that keeps agents honest: Claude lays work out as phases with a definition of done and a check, and whenever it tries to stop, Jevflow runs the checks and asks Jev whether the work is really done. Several agents can share one plan.
Jev Agents & MCP#community#catalog-import#logicrw
Community
parth1811/jevflowPython
parth1811/jevflowPythonOne skill and one MCP server for Claude Code, Codex and Hermes: Jev gates large-model turns with gate_triage, gate_verdict, gate_decide and gate_pick, runs build-and-repair loops with independent review, routes model tiers and skills, and guards Git steps.
Jev Agents & MCP#community#catalog-import#logicrw
Community
king4s/jev-ai-skillPython
king4s/jev-ai-skillPythonAn agent skill for Claude Code, Codex and other coding agents, with a standard-library Python CLI, 5 tested question sets and findings from 19,367 Jev calls and 90.4M metered input tokens over 4 days.
Jev Agents & MCP#community#catalog-import#logicrw
Community
marcodicesare-dev/jev-skillPython
marcodicesare-dev/jev-skillPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.