A FIELD GUIDE TO JEV / VOL. 01
Yang terbaik dari Jev: proyek nyata, panduan praktis, dan ide dari seluruh internet.
TypeSafe AI@typesafeaiOFFICIALTypeSafe highlights Jev’s typed-output approach: applications provide state and questions, then act on probabilities, choices or scores. The linked announcement also covers the Venice API integration.
x.comAnswers your code can useLihat proyek ↗TypeSafe AI@typesafeaiOFFICIALTypeSafe announces public access to Jev without a waiting list. The official console is the starting point for trying typed decisions in your own application.
x.comJev opens to everyoneLihat proyek ↗
Diogo Almeida@CompleteSkepticLAUNCH POSTDiogo Almeida introduces Jev, TypeSafe’s structured decision model. Watch the launch film and explore the original thread for the model’s approach, examples and author-reported performance.
TypeSafe AI@typesafeaiOFFICIALTypeSafe’s official launch announcement introduces the lab and points builders to Jev. It includes Diogo Almeida’s launch film and original introduction.
Four official signals. A fresh starting point on each visit.
378 sumber
AI-assisted summaries and translations. Check original sources for context and performance claims.
Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter.
github.comoso95/x-scannerLihat proyek ↗Source-linked curation
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/WinnowLihat proyek ↗Source-linked curation
Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM.
github.comprismhq/jev-routerLihat proyek ↗Source-linked curation
Marcel PociotMarcel Pociot's browser extension that collapses posts based on a Jev judgment.
Source-linked curation
Pi extension: verbatim context compaction with TypeSafe Jev decisions.
github.comjoelhooks/pi-fast-jev-compactionLihat proyek ↗Source-linked curation
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
github.comBentlybro/siftrLihat proyek ↗Source-linked curation
Pure Jev that can "type" and drive towards task completion.
github.combuluoray/JevOnlyLihat proyek ↗Source-linked curation
Route HTTP requests by meaning. A semantic router for Hono powered by Jev.
github.comyusukebe/hono-jev-routerLihat proyek ↗Source-linked curation
Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.
github.comarunav25/jev-mcpLihat proyek ↗Source-linked curation
A resource explaining Jev Engineering methodology for AI agent development.
Source-linked curation
A lightweight Jev-powered router for models, tools, and subagents.
github.comBillionsBobby/JevRouterLihat proyek ↗Source-linked curation
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
Source-linked curation
Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.
github.comchy4pro/jev-for-chromeLihat proyek ↗Source-linked curation
A Chrome extension that covers distracting YouTube videos with Jev. Show anyway whenever you want.
github.comjaibhasin/jev-yt-time-saverLihat proyek ↗Source-linked curation
A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.
Source-linked curation
Agent budget brake — continue / downgrade_model / stop via TypeSafe Jev.
github.comndolinschi/spendbrakeLihat proyek ↗Source-linked curation
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.
github.comshitianfang/jev-useLihat proyek ↗Source-linked curation
A GitHub project converting agent skills into Oxlint plugins that involve Jev.
Source-linked curation
Andy GaoA project using Jev to enable fast voice-controlled interactions with a Mac computer.
Source-linked curation
在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。
github.commanifoldor/xtagsLihat proyek ↗Source-linked curation
PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.
github.comanpicasso/hermes-jev-approvalsLihat proyek ↗Source-linked curation
Mormon NegroAn agent using headless Chromium to quickly navigate the web, demonstrated by browsing Wikipedia links efficiently.
Source-linked curation
A developer project for agent-native routing that selects models based on task complexity.
Source-linked curation
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-jevLihat proyek ↗Source-linked curation
Grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.
github.comkeltokhy/jgrepLihat proyek ↗Source-linked curation
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.
Source-linked curation
Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.
github.comCorieW/JevTestLihat proyek ↗Source-linked curation
A Magic 8 Ball for pull requests: click the ball and it answers "should I approve this?" with one of the 20 classic phrases, chosen by Jev from the PR's real signals in about 200 ms.
github.comacharyaanusha/magic-jevLihat proyek ↗Source-linked curation
Send Pi agents back to work when they stop before the job is done.
github.comalexshpunt/pi-agent-foremanLihat proyek ↗Source-linked curation
Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.
github.comomkarghugarkar007/actiongate-jevLihat proyek ↗Source-linked curation
Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.
github.comNainish-Rai/jev-frontend-qaLihat proyek ↗Source-linked curation
Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples.
github.comBodila51/grok-bot-jevLihat proyek ↗Source-linked curation
Select Git changes for staging with a plain-language description.
github.comibrahemid/git-jev-stageLihat proyek ↗Source-linked curation
TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.
github.comDECRUX9812/typesafe-skill-routerLihat proyek ↗Source-linked curation
Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev).
github.comeriestra/browser-use-olympicsLihat proyek ↗Source-linked curation
jev-use (voice). A developer project implementing voice control for macOS with Jev as a fallback option.
github.comcoco-research/jev-useLihat proyek ↗Source-linked curation
x.comA community experiment using Jev as a plugin in Claude to reduce unnecessary tool calls, cutting token count from 1M to 86K.
Source-linked curation
Jido agents use Jev to make moves in Tic Tac Toe, demonstrating Jev's application in game-playing agents.
Source-linked curation
Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.
github.comjgridifier/jev-research-evalLihat proyek ↗Source-linked curation
Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.
github.comussyverse/hermes-jev-routerLihat proyek ↗Source-linked curation
Official TypeSafe reference: Skill suggestion.
Source-linked curation
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.
github.comzhuyansen/jev-search-rerank-evalLihat proyek ↗Source-linked curation
Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.
github.comAbdelStark/bicameralLihat proyek ↗Source-linked curation
A tool ranking Pi agent skills for specific tasks using Jev's evaluation capabilities.
github.comsafzanpirani/pi-jev-skill-pickerLihat proyek ↗Source-linked curation
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Source-linked curation
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-2BLihat proyek ↗Source-linked curation
Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.
github.comaniruddh-krovvidi/switchboardLihat proyek ↗Source-linked curation
Matthew BermanJev analyzes 724 live ads from 37 brands in 40 seconds, breaking down their elements and formats.
Source-linked curation
An experiment using Jev for real-time model selection in AI agents, collected for the agents shelf.
Source-linked curation
Jev is integrated into tools like Noul and Score for MCP applications.
github.comandyholst/hermes-typesafe-jevLihat proyek ↗Source-linked curation
PauliusA system enabling rapid agent deployment on digital canvases without relying on slow LLM processes.
Source-linked curation
INSTRUCT_JEV - TypeSafe AI Jev / System One instruction corpus (choice/noul/score), compiled by DeckerGUI. 119 rows. Mirrored on HuggingFace.
github.comctaxnagomi/instruct-jevLihat proyek ↗Source-linked curation
jaffaA content marketing tool that analyzes 12.8M viral videos to generate data-backed social media scripts.
Source-linked curation
Local Instagram, TikTok, and LinkedIn research where Jev chooses bounded socai browser operations and streams captured evidence into cited reports.
github.comsocai-io/jev-socialLihat proyek ↗Source-linked curation
Reversible context pruning for Pi, powered by TypeSafe Jev. Keep useful context without deleting session history.
github.comkevinpita/pi-jev-contextLihat proyek ↗Source-linked curation
Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.
Source-linked curation
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.
github.comtorumitsutake/jev-page-verdictLihat proyek ↗Source-linked curation
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.
github.comnexibeo/jev-organizeLihat proyek ↗Source-linked curation
A developer project for agents and browsers, where Jev selects actions within Codex Computer Use.
github.comyikangy873-gif/jev-desktopLihat proyek ↗Source-linked curation
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.
github.comddfeyes/jev-modeLihat proyek ↗Source-linked curation
Alan DaitchAgent automates second-hand product search and decision-making. Processes 26 listings per minute with fast evaluation times.
Source-linked curation
JevNoiseGate filters unwanted notifications and SMS on Android. Rather than matching keywords, an LLM decides what's noise — and only what it explicitly flags is blocked. Verification codes are matched on-device and never uploaded; anything uncertain passes through.
github.comufec/jev-block-android-adLihat proyek ↗Source-linked curation
x.comAn article explains Jev's capabilities and highlights various projects built with it.
x.comWTF is Jev, and 9 things people are buildingLihat proyek ↗Source-linked curation
A developer project using Jev for plain-language MCP tool calls without an LLM.
Source-linked curation
A Chrome extension using Jev to filter out AI-generated content from YouTube, caching results for efficiency.
Source-linked curation
Route to the cheapest model in claude code for your task using jev-router.
Source-linked curation
A deterministic model routing system for coding agents with a skill for Codex.
Source-linked curation
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-belayLihat proyek ↗Source-linked curation
Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.
github.comMahmoudAdelbghany/jev-browserLihat proyek ↗Source-linked curation
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.
Source-linked curation
Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev.
github.comTheoOliveira/pi-jevLihat proyek ↗Source-linked curation
x.comExplains Jev's role in automating decision-making processes and enabling new business models through efficient task sorting and classification.
Source-linked curation
Kirim temuan
English
한국어
日本語
Español
Français
Deutsch
简体中文
繁體中文
Português
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
Agen & browser
Source-linked curation
RESMI