hermes-jev-skills
Project / 项目 · In the catalogue / 在目录中查看
What Jev decides here · Jev 在这里做什么决定
Model routing (模型路由), Context compaction (上下文压缩), Tool selection (工具选择)
choice, score, noul: read in the code by a person 由人在代码里读到
a person read the call site 有人读过调用点 · · Cited file / 引用的文件: jevkit/client.py
Summary · 摘要
Nine agent skills plus a CLI covering model routing, memory filtering, turn retention, one-of-many skill selection and next-action choice.
九个 agent 技能加一个 CLI，覆盖模型路由、记忆过滤、对话轮保留、多选一技能选择和下一步动作决策。
Notes · 备注
Notable for publishing a use it dropped: Jev-summarised handoffs had worse recall than raw transcripts.
值得一提的是它公开了一个被放弃的用法：用 Jev 做交接摘要的召回率，反而不如原始对话记录。
Launches · 发布记录
Not launched yet. 还没有发布过。 Launch it / 发布它 ↗ · How a product launches / 怎样发布一个产品
Makers · Maker
Made this? Confirm or correct its entry / 这是你做的？确认或更正条目 ↗
The same form takes the product's one line and a demo link, in its maker's own words. 同一个表单也可以补上产品的一句话和演示链接，用 Maker 自己的话。
Badge for its README · README 徽章
[](https://kydlikebtc.github.io/awesome-jev/products/hermes-jev-skills.html)One line for the product's README, linked to this page. The picture says that it is listed; while it is on the launch board, that it is launching; after a week in the top three, its place. It is rebuilt with the site, so the line never needs changing. 放进产品 README 的一行，链接到本页。图片显示已收录；在发布榜上时显示正在发布；进过某周前三后显示名次。它随网站一起重建，这一行不用再改。
Also under this pattern · 同一模式的其他产品
oh-my-pi
⌥ Coding agent with the IDE wired in
claude-code-templates: three Jev plugins
Three independently installable Claude Code plugins — guardrails, model router and skill suggestion — each with its own hooks and tests.
openwork
Open-source alternative to Claude Cowork, built on opencode. Its gateway's Auto route asks Jev one Score per Smart Router task and one for the thinking level, then routes the prompt by the answers; without a TypeSafe key it takes the fallback route.
@langchain/typesafe
The JavaScript counterpart of the LangChain integration, with the same classifier and middleware shapes.
distill
Coding-agent harness and TUI for Grok and Codex subscriptions and any OpenAI-compatible model, built to spend fewer tokens. When a model tier's effort is left on auto, the default, Jev picks the reasoning effort for every call; the client reaches Jev through OpenRouter by default.