A FIELD GUIDE TO JEV / VOL. 01

小さな判断。
大きな可能性。

Jevのプロジェクト、実践ガイド、世界中のアイデアをひとつに。

1,198件の資料16言語
TypeSafe AI THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POST

Jevのリリース投稿

ドイゴ・アレイダがJevを紹介し、TypeSafeの構造化された意思決定モデルを説明します。リリース映像を視聴し、オリジナルスレッドでモデルのアプローチ、例、および著者によるパフォーマンスを確認してください。

Start with the Launch Post. Explore four official signals.

286 件の資料

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。

fast-jev-compaction
Agents & browsersEnglish

Source-linked curation

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。

Jev Ultrafast
Agents & browsersEnglish

Source-linked curation

Clownware

Bouncer

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

Bouncer
Agents & browsersEnglish

Source-linked curation

itsmostafa

typesafe-mcp

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

typesafe-mcp
Agents & browsersEnglish

Source-linked curation

DanRWilloughby

snifftest

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

snifftest
Agents & browsersEnglish

Source-linked curation

Kush Bhuwalka

Jev Sift

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

Jev Sift
Agents & browsersEnglish

Source-linked curation

Agent Labs

fastbrowse

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

fastbrowse
Agents & browsersEnglish

Source-linked curation

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.

Verdict-open-jev
Agents & browsersEnglish

Source-linked curation

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.

jev-tool-runner
Agents & browsersEnglish

Source-linked curation

Raj Dhakad

routeKit

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

routeKit
Agents & browsersEnglish

Source-linked curation

droidrun

mobile-jev

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

mobile-jev
Agents & browsersEnglish

Source-linked curation

prasanth263

maza

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

maza
Agents & browsersEnglish

Source-linked curation

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.

jev-reviewer
Agents & browsersEnglish

Source-linked curation

kitze

unclutter

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

unclutter
Agents & browsersEnglish

Source-linked curation

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.

daf-jev
Agents & browsersEnglish

Source-linked curation

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。

typesafe-computer-use
Agents & browsersEnglish

Source-linked curation

AkashPriyadarshii

jev-superpowers

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

jev-superpowers
Agents & browsersEnglish

Source-linked curation

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.

yoshi
Agents & browsersEnglish

Source-linked curation

tamaratran

jev-pruner

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

jev-pruner
Agents & browsersEnglish

Source-linked curation

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.

skillranker
Agents & browsersEnglish

Source-linked curation

vercel

eve

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

eve
Agents & browsersEnglish

Source-linked curation

gaborishka

jev-canvas

Draw on a tldraw canvas with your voice and a pointing finger. Jev (TypeSafe System One) decides action, target and place in ~350 ms per spoken word.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

bestagentkits

jev-skillful

Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

romaluev

jev-ego

TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

wundercorp

Loki

Self-improving agent harness with an optional TypeSafe Jev companion for typed Choice, Score, and Noul judgments.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

Arslan R.

perfectrecall

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

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

altryne

jevify

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

GhalebDweikat

winnow

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

winnow
Agents & browsersEnglish

Source-linked curation

tontoko

jev-browser (tontoko)

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

jev-browser (tontoko)
Agents & browsersEnglish

Source-linked curation

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.

jev-voice-browser
Agents & browsersEnglish

Source-linked curation

torumitsutake

jev-page-verdict

Chrome extension that asks Jev whether the page you are on is selling something or reporting first-hand experience, and marks Google results with verdicts it already has or snippet-only estimates, leaving low-confidence ones undecided.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

Brainwires

jevwire

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

jevwire
Agents & browsersEnglish

Source-linked curation

harshwasan

pi-jev-sentinel

Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning).

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

leonaaardob

fast-dev-compaction

Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

MirkoSonio

jev-reflex

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

jev-reflex
Agents & browsersEnglish

Source-linked curation

tyler-dot-earth

patdown

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

patdown
Agents & browsersEnglish

Source-linked curation

phyous

tsai-civ2

TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

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.

jev-seo
Agents & browsersEnglish

Source-linked curation

NobleSpartan6

otto

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

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

keeltrace

hermes-jev

Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

RubyBrewsday

jevcumber

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

jevcumber
Agents & browsersEnglish

Source-linked curation

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 decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

KamilPostrozny

pi-jev-code

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

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

Icohen007

jev-play-ping-pong

Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

Bently

siftr

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

siftr
Agents & browsersEnglish

Source-linked curation

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 decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation

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.

tenbin
Agents & browsersEnglish

Source-linked curation

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.

JEVLAB decorative pixel illustration; not source mediaJEVLAB ART
Agents & browsersEnglish

Source-linked curation