小さな判断。
大きな可能性。

編集部のおすすめPopular on JEVLAB最新

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

翻訳要約4 clicks / 7d

tamaratran

fast-jev-compaction

Claude Codeプラグインで、コンパクションサマリーをJevの決定に置き換える。ツールコールと結果が1回の高速リクエストでスコア付けされ、古くなったものは破棄または切り詰められ、保持されるものは変更されない。

Agents & browsersEnglish

Source-linked curation

原文を開く

翻訳要約4 clicks / 7d

browser-use

Jev Ultrafast

ブラウザでの使用向けの超高速エージェント：Jevは1回のリクエストで操作とDOM要素を選択し、入力が必要な場合にのみ小さなLLMがテキストを書く。

Agents & browsersEnglish

Source-linked curation

原文を開く

tamaratran

jev-pruner

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

Agents & browsersEnglish

Source-linked curation

原文を開く

abhishekashokvkumar

jev-mcp-dispatcher

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

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く

Brainwires

jevwire

Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev).

Agents & browsersEnglish

Source-linked curation

原文を開く

Raj Dhakad

routeKit

A developer project for agent-native routing that selects models based on task complexity.

Agents & browsersEnglish

Source-linked curation

原文を開く

Konstantinos Botonakis

codex-context-diet

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

Agents & browsersEnglish

Source-linked curation

原文を開く

jkudish

jev-mcp (jkudish)

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

Agents & browsersEnglish

Source-linked curation

原文を開く

Nour

pi-jev-compaction

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

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く

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

原文を開く

gargpratyush

jev-router (gargpratyush)

Route to the cheapest model in claude code for your task using jev-router.

Agents & browsersEnglish

Source-linked curation

原文を開く

Tony Powell

jev-oxlint

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

Agents & browsersEnglish

Source-linked curation

原文を開く

DanRWilloughby

snifftest

A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.

Agents & browsersEnglish

Source-linked curation

原文を開く

brnyxx

jev-ra

Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.

Agents & browsersEnglish

Source-linked curation

原文を開く

GhalebDweikat

winnow

A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.

Agents & browsersEnglish

Source-linked curation

原文を開く

moritzkremb

jev-voice-browser

Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く

Agent Labs

fastbrowse

A developer project where Jev assists in browsing by selecting actions, with an LLM planning and citing sources.

Agents & browsersEnglish

Source-linked curation

原文を開く

AkashPriyadarshii

jev-seo

100% free ₹0 agent-first SEO & GEO CLI suite and MCP server in Rust replacing Semrush and OpenSEO via DuckDuckGo and TypeSafe Jev System One.

Agents & browsersEnglish

Source-linked curation

原文を開く

AkashPriyadarshii

jev-superpowers

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

Agents & browsersEnglish

Source-linked curation

原文を開く

Friedjof

jev-mobile

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

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く

itsmostafa

typesafe-mcp

Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex.

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く

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

原文を開く

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

原文を開く

devagrawal09

jev-review (devagrawal09)

A staged code-review workflow and local dashboard built with TypeSafe Jev.

Agents & browsersEnglish

Source-linked curation

原文を開く

madeye

pi-jev

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

Agents & browsersEnglish

Source-linked curation

原文を開く

yusukebe

hono-jev-router

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

github.comyusukebe/hono-jev-router詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

rainbowpuffpuff

jev-builder-loop

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

github.comrainbowpuffpuff/jev-builder-loop詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

Instructa

switchloom

A deterministic model routing system for coding agents with a skill for Codex.

Agents & browsersEnglish

Source-linked curation

原文を開く

0x7067

jev-browse (0x7067)

Browser automation with Jev (TypeSafe) as decision model.

github.com0x7067/jev-browse詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

Nyarlathoteppppp

pi-heed

Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.

Agents & browsersEnglish

Source-linked curation

原文を開く

y0usaf

pi-jev (y0usaf)

TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers.

github.comy0usaf/pi-jev詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

az9713

jev-model-router

Jev (TypeSafe) model router on the Vercel AI Gateway.

github.comaz9713/jev-model-router詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

leepokai

jev-guard

Prompt-injection and dangerous-action guard for coding agents (Claude Code, Codex, pi, ACP), powered by Jev.

github.comleepokai/jev-guard詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

BeLazy167

typesafe-mod

Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.

github.comBeLazy167/typesafe-mod詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

lomeshdutta

skill-router

Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.

github.comlomeshdutta/skill-router詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

krw82

jev-playwright-mcp

Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.

github.comkrw82/jev-playwright-mcp詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

wuyoscar

jev-skill

An awesome collection of Jev use cases, workflows, and agent skills.

github.comwuyoscar/jev-skill詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

matthewp

flue-jev-demo

Flue agent routing with TypeSafe Jev through Cloudflare AI Gateway.

github.commatthewp/flue-jev-demo詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

NobleSpartan6

otto

Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.

github.comNobleSpartan6/otto詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

socai-io

Jev Social

Local Instagram, TikTok, and LinkedIn research where Jev chooses bounded socai browser operations and streams captured evidence into cited reports.

github.comsocai-io/jev-social詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

vnmoorthy

siege

SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.

github.comvnmoorthy/siege詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く

bestagentkits

typesafe-demo-mcp

MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools.

github.combestagentkits/typesafe-demo-mcp詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

STRML

omp-jevens-classifier

Jev-powered model-judged permission gate for OMP (TypeSafe System One).

github.comSTRML/omp-jevens-classifier詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

VladyslavHontar

clear-head

Claude Code Stop hook that checks an AI assistant's claims against what it actually read this session, using TypeSafe's Jev as the judge.

github.comVladyslavHontar/clear-head詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

jomatsu

pi-jev-auto-mode

Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

github.comjomatsu/pi-jev-auto-mode詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

legacybridge-tech

pi-typesafe-jev

A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.

github.comlegacybridge-tech/pi-typesafe-jev詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

kikoncuo

jevfire

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

github.comkikoncuo/jevfire詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

Skyvern-AI

jevscape

RuneBench harness for TypeSafe's Jev: bounded action catalog, tick-mode controller and a live dashboard.

github.comSkyvern-AI/jevscape詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

vinilana

live-jev

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

github.comvinilana/live-jev詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

Bently

siftr

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

Agents & browsersEnglish

Source-linked curation

原文を開く

kerpopule

hermes-jev-skills

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex).

github.comkerpopule/hermes-jev-skills詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く

siddicky

omp-typesafe

TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent.

github.comsiddicky/omp-typesafe詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

DevMortimer

pi-warden

Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop.

github.comDevMortimer/pi-warden詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

0xNatoshi

jev-codex-router

Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

github.com0xNatoshi/jev-codex-router詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

CheshiAI

Cheshi

Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.

github.comCheshiAI/Cheshi詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

tacticocc

Jevbridge

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

github.comtacticocc/Jevbridge詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

翻訳要約

awlevin

typesafe-computer-use

ステップあたり約0.0002ドルでコンピュータを使用: スクリーンをOCRし、TypeSafeで次のアクションを分類し、クリックします。macOS対応。

Agents & browsersEnglish

Source-linked curation

原文を開く

bojansandhaus

jev-decisions

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

github.combojansandhaus/jev-decisions詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

RafalWilinski

vibecheck

Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post.

github.comRafalWilinski/vibecheck詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

kevinbadi

jev-voice

Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

github.comkevinbadi/jev-voice詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

ThinkyMiner

Winnow

Know before you click. A Chrome extension that reads articles and YouTube videos ahead of you and says read, skim, save, or skip — with a confidence, tuned to your goals. Open source, MV3, powered by Jev.

github.comThinkyMiner/Winnow詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

caiovicentino

jev-shield

Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

github.comcaiovicentino/jev-shield詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

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.

github.comlukaske/jev-doom-agent詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

eugeniughelbur

jev-engineering

Decision layer for coding agents: deterministic rules before any model call, then one Jev request, as a Claude Code PreToolUse hook, an MCP server, a loopback service and a team policy that personal overrides can tighten but not loosen. Ships the 300-call injection kit behind its own numbers.

github.comeugeniughelbur/jev-engineering詳しく見る ↗

Agents & browsersEnglish

Source-linked curation

原文を開く

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

原文を開く