小小判断。
无限可能。

编辑精选Popular on JEVLAB最新

AI-assisted summaries and translations. Check original sources for context and performance claims.

译文摘要4 clicks / 7d

tamaratran

fast-jev-compaction

Claude代码插件通过Jev决策替换压缩摘要，通过一次快速请求对每个工具调用和结果进行评分，过时的调用会被丢弃或截断，所有保留的内容保持原样。

Agents & browsersEnglish

Source-linked curation

查看原文

译文摘要4 clicks / 7d

browser-use

Jev Ultrafast

浏览器使用中的超快速代理：Jev在一次请求中选择操作和DOM元素；仅当需要输入时，小型LLM才编写文本。

Agents & browsersEnglish

Source-linked curation

查看原文

Pedro Knigge

mcp_jev

A developer project providing a local MCP server for running pre-made Jev question packs.

Agents & browsersEnglish

Source-linked curation

查看原文

Dicklesworthstone

skillranker

Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

Agents & browsersEnglish

Source-linked curation

查看原文

shiftynick

jev-axi

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.

Agents & browsersEnglish

Source-linked curation

查看原文

Clownware

Bouncer

An agent project that enforces policies by judging Claude Code tool calls.

Agents & browsersEnglish

Source-linked curation

查看原文

tyler-dot-earth

patdown

Typesafe's jev as a "fuzzy linter". give your code an ocular patdown.

Agents & browsersEnglish

Source-linked curation

查看原文

tamaratran

jev-pruner

Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.

Agents & browsersEnglish

Source-linked curation

查看原文

compozy

yoshi

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy.

Agents & browsersEnglish

Source-linked curation

查看原文

luantak

is-malicious

Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.

Agents & browsersEnglish

Source-linked curation

查看原文

24601

Augustus

Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.

Agents & browsersEnglish

Source-linked curation

查看原文

Friedjof

jev-mobile

Fast structured Android control loops with TypeSafe Jev and Mobile MCP.

Agents & browsersEnglish

Source-linked curation

查看原文

prasanth263

maza

A developer project for the agents shelf featuring a local MCP gateway with Jev tool discovery and a dashboard.

Agents & browsersEnglish

Source-linked curation

查看原文

docxology

daf-jev

Daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill.

Agents & browsersEnglish

Source-linked curation

查看原文

droidrun

mobile-jev

Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.

Agents & browsersEnglish

Source-linked curation

查看原文

Ying-Kai-Liao

jev-browser (Ying-Kai-Liao)

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

Agents & browsersEnglish

Source-linked curation

查看原文

kitze

unclutter

WXT browser extension: Jev-powered page clutter removal with reusable template rules.

Agents & browsersEnglish

Source-linked curation

查看原文

Mihajlo Micic

jev-tool-runner

Jev-Tool-Runner is a GitHub project where Jev selects developer tools and Codex generates code based on those selections.

Agents & browsersEnglish

Source-linked curation

查看原文

MirkoSonio

jev-reflex

A developer project demonstrates Jev's rapid response to browser tasks, with decisions made in approximately 100 milliseconds.

Agents & browsersEnglish

Source-linked curation

查看原文

Konstantinos Botonakis

codex-context-diet

A Codex plugin that uses Jev to streamline and reduce excessive tool outputs.

Agents & browsersEnglish

Source-linked curation

查看原文

Nour

pi-jev-compaction

A developer project for automatic context clearing in Pi without losing conversation history.

Agents & browsersEnglish

Source-linked curation

查看原文

skeptrunedev

jev-recruiter

A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.

Agents & browsersEnglish

Source-linked curation

查看原文

tontoko

jev-browser (tontoko)

One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.

Agents & browsersEnglish

Source-linked curation

查看原文

vercel

eve

Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.

Agents & browsersEnglish

Source-linked curation

查看原文

Tony Powell

jev-oxlint

A GitHub project converting agent skills into Oxlint plugins that involve Jev.

Agents & browsersEnglish

Source-linked curation

查看原文

Heman10x-NGU

Verdict-open-jev

Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground.

Agents & browsersEnglish

Source-linked curation

查看原文

dbreunig

building-with-jev-skill

A skill for writing and improving programs that call Jev, TypeSafe's System One model.

Agents & browsersEnglish

Source-linked curation

查看原文

madeye

pi-jev

Jev-assisted file retrieval and request caching for faster Pi workflows.

Agents & browsersEnglish

Source-linked curation

查看原文

jkudish

jev-mcp (jkudish)

Proof of concept MCP for Typesafe's new Jev AI model.

Agents & browsersEnglish

Source-linked curation

查看原文

Bently

siftr

A developer project offering semantic code search for coding agents, benchmarked on SWE-bench Lite.

Agents & browsersEnglish

Source-linked curation

查看原文

rashedInt32

jev-mcp (rashedInt32)

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

AkashPriyadarshii

jev-superpowers

Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.

Agents & browsersEnglish

Source-linked curation

查看原文

GodsBoy

jev-agent-skill-router

Typed, confidence-aware agent skill routing with TypeSafe Jev.

Agents & browsersEnglish

Source-linked curation

查看原文

JanOstrowka

typesafe-assist

Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

choxos

jev-reviewer

Data extraction for systematic reviews, quoted from the papers. Ask a trial report and its supplements your extraction form or a RoB 2, ROBINS-I, QUADAS-2 or TIDieR template; Jev points at the lines, every answer is a verbatim quote with its page, you check it and export the table. Files stay in your browser.

Agents & browsersEnglish

Source-linked curation

查看原文

AkashPriyadarshii

jev-git

Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

ndolinschi

harnessjudge

Judge agent steps — ok / retry / escalate / stop via TypeSafe Jev.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

ddfeyes

jev-mode

I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

RubyBrewsday

jevcumber

Write Cucumber tests with just the .feature file. No step definitions — Jev (TypeSafe AI) resolves each Gherkin step and Playwright runs it.

Agents & browsersEnglish

Source-linked curation

查看原文

Ripwords

agent-gate-loop

Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

jvsteiner

jevex

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

bojansandhaus

jev-decisions

Safety checks for Hermes and other AI agents before they act, ask for approval, or verify a change.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

rbalch

typesafeai-review

Using Typesafe.AI to generate diff reviews.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

KamilPostrozny

pi-jev-code

Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

getexcited

stepwarden

Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

shitianfang

jev-use

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

vinilana

live-jev

2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

Hitakshi Arora

solari-reflex

An agent system that makes one Jev decision per computational step.

Agents & browsersEnglish

Source-linked curation

查看原文

thruwire

foreman

Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

HyunjunJeon

jev-judgment

Agent Skill: send closed coding-agent judgments to TypeSafe Jev.

Agents & browsersEnglish

Source-linked curation

查看原文

zhuyansen

jev-search-rerank-eval

Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

omni-

ask-jev

Utilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

yusukebe

hono-jev-router

Route HTTP requests by meaning. A semantic router for Hono powered by Jev.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

mkeco

Cerebellum-2B

Non-Autoregressive AI Agent Decision Model. Open-source SOTA alternative to TypeSafe Jev. O(1) Tool Routing & DOM Automation on Qwen3.5-2B .

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

moezubair

check-risk

A CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

lukaske

jev-doom-agent

A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

oso95

x-scanner

Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

nexibeo

jev-organize

Throw in a pile of company files and get them classified and organized by department, type, sensitivity, date, counterparty and PII, with an index for AI agents. Powered by TypeSafe's Jev on OpenRouter (17¢ per 1,000 files). Zero-dependency Node CLI + Claude skill + Codex agent.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

译文摘要

aniruddh-krovvidi

switchboard

基于TypeSafe的Jev（System One模型）的LLM网关的防护机制+模型路由器，包含独立的准确性/校准/延迟评估。标准库Python。

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

rainbowpuffpuff

jev-builder-loop

Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act).

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

DanielKillenberger

jev-predict-skill

Predict another skill's next closed decision with TypeSafe Jev — without running that skill.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

0x7067

jev-browse (0x7067)

Browser automation with Jev (TypeSafe) as decision model.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

simota

tenbin

MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code.

Agents & browsersEnglish

Source-linked curation

查看原文

marcus

frost

A flexible and configurable CLI model router using TypeSafe Jev.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

abhishekashokvkumar

jev-mcp-dispatcher

A developer project using Jev for plain-language MCP tool calls without an LLM.

Agents & browsersEnglish

Source-linked curation

查看原文

Eronmonsele Aigbiluese

jev-cua

A local computer-use fast path for Codex and Waku, designed for developers.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

Arslan R.

perfectrecall

A developer project focused on agent memory, where Jev determines what information is relevant to recall.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

CodeAlive-AI

mastra-jev-moderation

Input moderation for Mastra agents on TypeSafe Jev — one file.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

Kush Bhuwalka

Jev Sift

A developer project for agent classification and selective reading using an agent plugin and MCP tool.

Agents & browsersEnglish

Source-linked curation

查看原文

CodeAlive

mastra-jev-moderation

A moderation system for Mastra agents that processes inputs in a single file.

Agents & browsersEnglish

Source-linked curation

查看原文

Andy Holst

hermes-typesafe-jev

Jev is integrated into tools like Noul and Score for MCP applications.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文

nexibeo

jev-cookbook

Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent.

JEVLAB ART

Agents & browsersEnglish

Source-linked curation

查看原文