小小判斷。
無限可能。

所有語言優先我的語言僅我的語言編輯精選Popular on JEVLAB最新

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

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

SuperTurbo

Hawk or dove?

A project comparing Jev's performance against chat models in analyzing Fed press conferences.

Markets & experimentsEnglish

Source-linked curation

查看原文

TrainLCD

TrainLCD Jev rerank

Pull request adding Jev to station-suggestion reranking in the TrainLCD transit app.

github.comTrainLCD/Functions/pull/33查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

AstroHan

jev-harness

A developer project where Jev filters tool results before model processing, aiming to improve efficiency in agent systems.

github.comAstro-Han/jev-harness查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

numerous-com

DGP (Decision Graph Protocol)

Experimental decision protocol whose Jev adapter evaluates framed evidence with typed choices, while application code validates permissions and commits simulated demo actions.

github.comnumerous-com/dgp查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

TypeSafeAI

typesafe-ui

Shadcn-style reusable components and blocks for using TypeSafe AI.

github.comTypeSafeAI/typesafe-ui查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

Abid A Gafoor

capture

A Mac voice diary tool that uses Jev for sorting and integrates with Notion.

Tools & appsEnglish

Source-linked curation

查看原文

blas0

jev-shadcn-lint-eval

A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.

github.comblas0/jev-shadcn-lint-eval查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

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查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

Gaurav-Gosain

jev-headline-bench

Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive.

github.comGaurav-Gosain/jev-headline-bench查看專案 ↗

Research & dataEnglish

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 .

github.commkeco/Cerebellum-2B查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

iamvatsalpatel

tiershift

Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.

github.comiamvatsalpatel/tiershift查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

zefir1990

openjev-experiments

Experiments with openjev, an open Jev-style option-logit runner, on local models.

github.comzefir1990/openjev-experiments查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

Okina Audio

live-jev

A tool controlling Ableton Live with concise commands, leveraging Jev's decision-making capabilities.

github.comokinaaudio/live-jev查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

DeepBlueDynamics

typesafe-arena

A playground for TypeSafeAI's Jev Model.

github.comDeepBlueDynamics/typesafe-arena查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

精選譯文摘要1 clicks / 7d

typesafe-ai

System One 介面（Python）

支援 OpenAI、Anthropic 及相容 LLM API 的官方 TypeSafeClient 替代品，用於比較 Jev 與聊天模型。

github.comtypesafe-ai/system-one-adapter-python查看專案 ↗

Start hereEnglish

Source-linked curation

查看原文

sgoedecke

system-one

Batched single-token choice inference for open language models, compatible with TypeSafe.

github.comsgoedecke/system-one查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

sorrycc

typesafe-snake

Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.

github.comsorrycc/typesafe-snake查看專案 ↗

Games & real timeEnglish

Source-linked curation

查看原文

dannote

jev (dannote)

TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer.

github.comdannote/jev查看專案 ↗

Tools & appsEnglish

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

Chao Qin

pi-jev-router (win4r)

A developer project for model routing with caching and failover.

github.comwin4r/pi-jev-router查看專案 ↗

Decisions & routingEnglish

Source-linked curation

查看原文

shantanugoel

ask-jev-skill

Skill for Hermes, and other agents, to ask typesafe's jev.

github.comshantanugoel/ask-jev-skill查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

sriganesh

jevibe-check

A live tone labeler for Bluesky posts and drafts, using TypeSafe's Jev API.

github.comsriganesh/jevibe-check查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

vinilana

jev-eval-agent

Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.

github.comvinilana/jev-eval-agent查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

qkal

Canny

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

github.comqkal/Canny查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

bestagentkits

typesafe-demo-mcp

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

github.combestagentkits/typesafe-demo-mcp查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

RafalWilinski

vibecheck

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

github.comRafalWilinski/vibecheck查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

Malek Gara-Hellal

guesswork

A tool enhancing zsh autosuggestions with Jev-based ranking instead of prefix matching.

Creative & growthEnglish

Source-linked curation

查看原文

tonyzdev

pijev

PiJev: a terminal coding agent with Jev in the loop — Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi.

github.comtonyzdev/pijev查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

Kevthetech143

super-jev

A small, extensible decision-to-action harness for TypeSafe Jev.

Tools & appsEnglish

Source-linked curation

查看原文

Ngoc Phan

browser-ai

A Jev browser agent implemented in Go, connected to a real Chrome browser for agent-based tasks.

github.comphanngoc/browser-ai查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

WebGrga

jev-board-lab

Interactive explorer and Jev question workspace for Jev Board datasets.

github.comWebGrga/jev-board-lab查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

valentynkit

jev-belay

Claude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else.

github.comvalentynkit/jev-belay查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

ShuhanSun

jev-oas-sentinel

Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.

github.comShuhanSun/jev-oas-sentinel查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

elpumberto

barrunto

A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse.

github.comelpumberto/barrunto查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

danielgshea

jev-as-a-judge

Using Jev as an evaluator.

github.comdanielgshea/jev-as-a-judge查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

TheoOliveira

pi-jev (TheoOliveira)

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev.

github.comTheoOliveira/pi-jev查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

shantanugoel

jev-games

Visual Jev lab for multiple games and emulator platforms.

github.comshantanugoel/jev-games查看專案 ↗

Games & real timeEnglish

Source-linked curation

查看原文

Butochnikov

laravel-typesafe-jev

Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes.

github.comButochnikov/laravel-typesafe-jev查看專案 ↗

Start hereEnglish

Source-linked curation

查看原文

phyous

tsai-civ2

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

github.comphyous/tsai-civ2查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

jh1373

jev-search

Offline Obsidian search with optional Jev reranking of results, requiring user approval before reranking.

Research & dataEnglish

Source-linked curation

查看原文

mblode

taste-lint

CLI that uses Jev to catch AI slop in UI, copy, and agent instructions before ship (probabilities on semantic taste checks).

github.commblode/taste-lint查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

jomatsu

zod-jev

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

github.comjomatsu/zod-jev查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

codeitlikemiley

typesafe-sdk-rust

Rust SDK for the TypeSafe AI API.

github.comcodeitlikemiley/typesafe-sdk-rust查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

YehuiTang0316

nlgrep

TypeScript CLI that finds code, docs, logs, and text by natural-language conditions using Jev Noul judgments, with probability thresholds, source lines, and cached results.

github.comYehuiTang0316/jev-nlgrep查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

wundercorp

Loki

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

github.comwundercorp/loki查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

fgn

jevgo

Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation.

github.comfgn/jevgo查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

Raj Dhakad

routeKit

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

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

WiktorB2004

llama-index-jev

LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.

github.comWiktorB2004/llama-index-jev查看專案 ↗

Decisions & routingEnglish

Source-linked curation

查看原文

choxos

jevchess

Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates.

github.comchoxos/jevchess查看專案 ↗

Games & real timeEnglish

Source-linked curation

查看原文

Nolane-x

JEV-language

Give your Jev language.

github.comNolane-x/JEV-language查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

Red5d

jev-cvss

Fast CVSS scoring from vulnerability descriptions using Typesafe Jev.

github.comRed5d/jev-cvss查看專案 ↗

Decisions & routingEnglish

Source-linked curation

查看原文

Bud-ro

jev-demos

Demos to test the effectiveness of TypeSafe's "Jev" System One Model.

github.comBud-ro/jev-demos查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

EugeneBoondock

jevsql

SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded.

github.comEugeneBoondock/jevsql查看專案 ↗

Decisions & routingEnglish

Source-linked curation

查看原文

Allen Porter

home-assistant-typesafe

A developer project integrating Home Assistant with Jev for processing user input without an LLM.

github.comallenporter/home-assistant-typesafe查看專案 ↗

Decisions & routingEnglish

Source-linked curation

查看原文

logan-markewich

jeff

A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.

github.comlogan-markewich/jeff查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

Filed

playjev

Playjev uses Jev for browser automation with decision-making capabilities.

github.comfiledcom/playjev查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

realZachi

pg-jev

Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.

github.comrealZachi/pg-jev查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

scienthoon

jev-ood-calibration

Independent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.

github.comscienthoon/jev-ood-calibration查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

rajdhakad9826

jev-router

Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.

github.comrajdhakad9826/jev-router查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

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查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

Icohen007

jev-play-ping-pong

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

github.comIcohen007/jev-play-ping-pong查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

Kiln-AI

jev_jsonschema

Run a JSON Schema through TypeSafe's Jev API, and get JSON back.

github.comKiln-AI/jev_jsonschema查看專案 ↗

Tools & appsEnglish

Source-linked curation

查看原文

FerryCorleone

crush-monitor

A tool that analyzes WeChat threads for emotion, intent, and reply quality.

github.comFerryCorleone/crush-monitor查看專案 ↗

Creative & growthEnglish

Source-linked curation

查看原文

CorieW

JevTest

Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.

github.comCorieW/JevTest查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

wfzyx

von

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

github.comwfzyx/von查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

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

查看原文

razorback16

openjev

Open, Jev-compatible System One decision server on DiffusionGemma.

github.comrazorback16/openjev查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

vehas

thaiexam-jev-charts

Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models.

github.comvehas/thaiexam-jev-charts查看專案 ↗

Research & dataEnglish

Source-linked curation

查看原文

CrowdLinker

JevPromptCoach

Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.

github.comCrowdLinker/JevPromptCoach查看專案 ↗

Agents & browsersEnglish

Source-linked curation

查看原文

safzanpirani

pong-jev

TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model.

github.comsafzanpirani/pong-jev查看專案 ↗

Games & real timeEnglish

Source-linked curation

查看原文