S
shitianfang/jev-use
Hand steps that need no prose to a small judgment model
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项（本地服务器用 command + args，示例见 客户端接法） - 重启客户端
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"shitianfang-jev-use": {
"command": "npx",
"args": ["-y", "jev-use"]
}
}
}解析自我们于 2026-11-05 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"shitianfang-jev-use": {
"command": "npx",
"args": ["-y", "jev-use"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio shitianfang-jev-use -- npx -y jev-use
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单（我们从中收集的条目之一） · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
npx -y jev-use
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx -y jev-use。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: MCP 服务。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
我们收录于 2026-11-05；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
# jev-use
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
English | 简体中文
The best way for Claude Code, Codex, and pi
to work with Jev:
hand the tasks that need no text output to Jev — faster steps, fewer
tokens, tasks done sooner and better.
It makes the LLM and Jev true collaborators: when content needs to be
written, the LLM takes over; when a step just needs a fast decision, Jev
executes it.
## Demos — real runs, 1× speed
Directions task: Jev clicks, the LLM types — 10 decisions (p50 274 ms) · 4 writes; Jev rejects a wrong route, the LLM rewrites
Context compaction — 200 messages judged in 7 calls, one LLM paragraph replaces the dropped pile; recall 3/3
Pong: ball speed = decision latency — 86 Jev decisions in 20 s vs 6 (haiku) and 3 (gemini) called the usual way; enum-constrain both and the gap is 3×
Gate every shell command — dangerous ones denied in ~230 ms with a reason, zero LLM tokens
Every demo is a rerunnable script in bench/examples/;
all numbers, methodology, variance and caveats:
bench/RESULTS.md · third-party measurements:
docs/evidence.md.
## Install
bash
npx -y jev-use install # wires Claude Code, Codex, and pi — whichever it finds
Set one key in the environment your agent runs in (JEVBACKEND=mock for
a keyless dry run):
| Provider | Env var |
| TypeSafe direct | TYPESAFEAPIKEY |
| OpenRouter | OPENROUTERAPIKEY |
| Vercel AI Gateway | AIGATEWAYAPIKEY |
npx -y jev-use doctor checks the wiring. Judged state goes to the
provider you configure; JEVBACKEND=mock stays local. Plugin form with
the routing skill and the PreToolUse gate:
harness/claude-code ·
harness/codex.
## Use as a library
npm i jev-use — zero runtime dependencies on the judgment path:
js
import { Jev, check, pick, rate } from "jev-use";
const jev = new Jev();
const { answers } = await jev.judge(state, {
next: pick("Next action?", { merge: "all green", rerun: "looks flaky", hold: "needs attention" }),
risk: rate("How risky?", ["routine", "worth a look", "incident"]),
passed: check("Did the run fully succeed?"),
});
// answers.next → { answer: "merge", confidence: 0.93, confidenceFrom: "reported", escalate: false }
Anything Jev can't or shouldn't decide comes back with escalate: true
and a typed reason. Tools, verdict shape, escalation contract, CLI:
docs/reference.md.
## Small enough to read
| File | Job |
| src/protocol.ts | Questions (check/pick/rate), verdicts, escalation reasons |
| src/dispatch.ts | Pre-call routing: what never reaches Jev |
| src/judge.ts | screen → backend → hand back what is unsure; gate |
The best way for Claude Code, Codex, and pi
to work with Jev:
hand the tasks that need no text output to Jev — faster steps, fewer
tokens, tasks done sooner and better.
It makes the LLM and Jev true collaborators: when content needs to be
written, the LLM takes over; when a step just needs a fast decision, Jev
executes it.
## Demos — real runs, 1× speed
Directions task: Jev clicks, the LLM types — 10 decisions (p50 274 ms) · 4 writes; Jev rejects a wrong route, the LLM rewrites
Context compaction — 200 messages judged in 7 calls, one LLM paragraph replaces the dropped pile; recall 3/3
Pong: ball speed = decision latency — 86 Jev decisions in 20 s vs 6 (haiku) and 3 (gemini) called the usual way; enum-constrain both and the gap is 3×
Gate every shell command — dangerous ones denied in ~230 ms with a reason, zero LLM tokens
Every demo is a rerunnable script in bench/examples/;
all numbers, methodology, variance and caveats:
bench/RESULTS.md · third-party measurements:
docs/evidence.md.
## Install
bash
npx -y jev-use install # wires Claude Code, Codex, and pi — whichever it finds
Set one key in the environment your agent runs in (JEVBACKEND=mock for
a keyless dry run):
| Provider | Env var |
| TypeSafe direct | TYPESAFEAPIKEY |
| OpenRouter | OPENROUTERAPIKEY |
| Vercel AI Gateway | AIGATEWAYAPIKEY |
npx -y jev-use doctor checks the wiring. Judged state goes to the
provider you configure; JEVBACKEND=mock stays local. Plugin form with
the routing skill and the PreToolUse gate:
harness/claude-code ·
harness/codex.
## Use as a library
npm i jev-use — zero runtime dependencies on the judgment path:
js
import { Jev, check, pick, rate } from "jev-use";
const jev = new Jev();
const { answers } = await jev.judge(state, {
next: pick("Next action?", { merge: "all green", rerun: "looks flaky", hold: "needs attention" }),
risk: rate("How risky?", ["routine", "worth a look", "incident"]),
passed: check("Did the run fully succeed?"),
});
// answers.next → { answer: "merge", confidence: 0.93, confidenceFrom: "reported", escalate: false }
Anything Jev can't or shouldn't decide comes back with escalate: true
and a typed reason. Tools, verdict shape, escalation contract, CLI:
docs/reference.md.
## Small enough to read
| File | Job |
| src/protocol.ts | Questions (check/pick/rate), verdicts, escalation reasons |
| src/dispatch.ts | Pre-call routing: what never reaches Jev |
| src/judge.ts | screen → backend → hand back what is unsure; gate |
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/shitianfang-jev-use/)
- 来源
- awesome · https://github.com/shitianfang/jev-use
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。