jev-use

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

npx -y jev-use install    # wires Claude Code, Codex, and pi — whichever it finds

Set one key in the environment your agent runs in (JEV_BACKEND=mock for a keyless dry run):

Provider	Env var
TypeSafe direct	TYPESAFE_API_KEY
OpenRouter	OPENROUTER_API_KEY
Vercel AI Gateway	AI_GATEWAY_API_KEY

npx -y jev-use doctor checks the wiring. Judged state goes to the provider you configure; JEV_BACKEND=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:

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
src/jev.ts	The Jev client over that engine
src/redact.ts	Credentials stripped from a gated action before it is sent
src/backends/	TypeSafe, OpenRouter, Vercel, mock adapters
src/server.ts	The two MCP tools
src/cli.ts	install, serve, hook gate, doctor
skills/jev-use/SKILL.md	The routing rules the agent follows

Development

$ npm run typecheck && npm test    # unit tests incl. per-provider wire fixtures
$ npm run smoke                    # real MCP client ↔ built CLI over stdio
$ node bench/run.mjs               # micro-benchmarks, your key and region

Substantially written with Claude Code (AI-assisted).

MIT © shitianfang