A FIELD GUIDE TO JEV / VOL. 01
Лучшее о Jev: реальные проекты, практические руководства и идеи со всего интернета.
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.
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 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 useПодробнее о проекте ↗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 everyoneПодробнее о проекте ↗Four official signals. A fresh starting point on each visit.
378 материалов
AI-assisted summaries and translations. Check original sources for context and performance claims.
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-adПодробнее о проекте ↗Source-linked curation
One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.
Source-linked curation
Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.
github.comomkarghugarkar007/actiongate-jevПодробнее о проекте ↗Source-linked curation
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-wardenПодробнее о проекте ↗Source-linked curation
Matthew BermanJev analyzes 724 live ads from 37 brands in 40 seconds, breaking down their elements and formats.
Source-linked curation
Pure Jev that can "type" and drive towards task completion.
github.combuluoray/JevOnlyПодробнее о проекте ↗Source-linked curation
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
github.comagent-chaperone/agent-chaperoneПодробнее о проекте ↗Source-linked curation
An experiment using Jev for real-time model selection in AI agents, collected for the agents shelf.
Source-linked curation
Experimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent.
github.comzsoXi/agent-handoff-gateПодробнее о проекте ↗Source-linked curation
A developer project for agent classification and selective reading using an agent plugin and MCP tool.
Source-linked curation
x.comLists six specific tasks where Jev is used for fact-checking, ranking, text finding, citation checking, note grouping, and agent failure analysis.
x.comSix things I will still use Jev forПодробнее о проекте ↗Source-linked curation
A guide explaining how to integrate Jev with Pydantic AI agents for type-safe operations.
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-jevПодробнее о проекте ↗Source-linked curation
Judge agent steps — ok / retry / escalate / stop via TypeSafe Jev.
github.comndolinschi/harnessjudgeПодробнее о проекте ↗Source-linked curation
x.comA community post describing Jev as a decision-making tool with specific limitations and use cases.
x.comA hype-free explanation of JevПодробнее о проекте ↗Source-linked curation
An awesome collection of Jev use cases, workflows, and agent skills.
github.comwuyoscar/jev-skillПодробнее о проекте ↗Source-linked curation
RanjanA community project enabling hands-free web navigation by having Jev handle browser actions while Claude manages conversation.
Source-linked curation
A developer project for the agents shelf, using MCP tool for Codex instead of listing all options.
github.comjackbarunz/jev-tool-routerПодробнее о проекте ↗Source-linked curation
Using Typesafe.AI to generate diff reviews.
github.comrbalch/typesafeai-reviewПодробнее о проекте ↗Source-linked curation
OskarFramework for running end-to-end tests with agents using Jev.
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-organizeПодробнее о проекте ↗Source-linked curation
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/tiershiftПодробнее о проекте ↗Source-linked curation
Uses typeful jev, zero sync to pull and sync large repositories for issue triage.
github.comcephalization/jev-triageПодробнее о проекте ↗Source-linked curation
x.comA community post explaining Jev's role in improving agent efficiency and cost-effectiveness.
x.comHow Jev makes agents faster and cheaperПодробнее о проекте ↗Source-linked curation
TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate.
github.comajensenwaud/hermes-jev-pluginПодробнее о проекте ↗Source-linked curation
Milind SA system using Jev to interact with computer interfaces without screenshots, relying on local CoreML models and OCR.
Source-linked curation
DGUI-HyperMem (DeckerGUI HyperMemory) - self-hosted hybrid memory MCP server on Cloudflare Workers with a JEV (Choice/Noul/Score) reasoning layer and a HuggingFace training-brain flywheel.
github.comctaxnagomi/dgui-hypermemПодробнее о проекте ↗Source-linked curation
Browser use using Typesafe's Jev model.
github.comjkudish/jev-browserПодробнее о проекте ↗Source-linked curation
Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One.
github.comopaielsheikh/ps2-ai-agentПодробнее о проекте ↗Source-linked curation
Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.
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-approvalsПодробнее о проекте ↗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 buildingПодробнее о проекте ↗Source-linked curation
A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.
github.comscale-venture-partners/riffПодробнее о проекте ↗Source-linked curation
A tested resource evaluating Jev's capabilities in browser automation and support tasks.
YouTube · Подробнее о проектеSource-linked curation
Marcel PociotMarcel Pociot's browser extension that collapses posts based on a Jev judgment.
Source-linked curation
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
Source-linked curation
Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.
github.comShivamPansuriya/jev-skill-gateПодробнее о проекте ↗Source-linked curation
x.comA community post outlines a guide for constructing a high-speed agent brain using Jev.
x.comBuilding the fastest agent brain in 10 stepsПодробнее о проекте ↗Source-linked curation
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.
github.combestagentkits/jev-skillfulПодробнее о проекте ↗Source-linked curation
A developer project where Jev assists in browsing by selecting actions, with an LLM planning and citing sources.
Source-linked curation
Route tasks to research/code/browser/support/writer agents via TypeSafe Jev.
github.comndolinschi/swarmrouterПодробнее о проекте ↗Source-linked curation
A community project exploring Jev's potential to evaluate agent progress beyond basic trace data.
Source-linked curation
Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.
Source-linked curation
Browser game: try to beat Jev at spotting a spam message.
github.comlambertsj/beatjevПодробнее о проекте ↗Source-linked curation
Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels.
github.cominanna-malick/jev-dslПодробнее о проекте ↗Source-linked curation
Agent makes rapid shopping decisions using Ego Lite and Jev. Completes 20 product evaluations in under 4 seconds.
Source-linked curation
A developer project using Jev for plain-language MCP tool calls without an LLM.
Source-linked curation
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/JevPromptCoachПодробнее о проекте ↗Source-linked curation
A tool ranking Pi agent skills for specific tasks using Jev's evaluation capabilities.
github.comsafzanpirani/pi-jev-skill-pickerПодробнее о проекте ↗Source-linked curation
Task plus subscription list in, Jev picks which model or agent should handle it.
x.comModel router CLIПодробнее о проекте ↗Source-linked curation
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-jevПодробнее о проекте ↗Source-linked curation
Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.
github.comKesavanKing/jev-browserПодробнее о проекте ↗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-belayПодробнее о проекте ↗Source-linked curation
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-shieldПодробнее о проекте ↗Source-linked curation
Browser extension that reads the YouTube caption track and paints a per-segment sponsor probability on the seek bar before the intro ends, with no crowd database.
github.comvalentynkit/jev-skipПодробнее о проекте ↗Source-linked curation
TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.
github.comphyous/tsai-civ2Подробнее о проекте ↗Source-linked curation
Ultra-fast model routing using Jev for agent-based systems.
Source-linked curation
Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.
github.commolis-ai/jev-workbenchПодробнее о проекте ↗Source-linked curation
An agent project that enforces policies by judging Claude Code tool calls.
Source-linked curation
Pre-commit hook: one Jev call judges whether your commit message matches the staged diff, plus debug leftovers, unmentioned work, and a credential check.
github.comvalentynkit/jev-commitПодробнее о проекте ↗Source-linked curation
Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.
Source-linked curation
Official TypeSafe reference: Skill suggestion.
Source-linked curation
Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.
github.comkevinbadi/jev-voiceПодробнее о проекте ↗Source-linked curation
Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook.
github.comRiskAverseTech/toolgateПодробнее о проекте ↗Source-linked curation
NotteJev automates browser tasks by selecting actions from a dynamic action space.
Source-linked curation
Six hook gates for Claude Code that catch broken rules, out-of-scope edits, unfinished asks, and false claims, each judged by Jev against a fixed checklist and one piece of evidence.
github.comrashedInt32/jev-gatesПодробнее о проекте ↗Source-linked curation
A lightweight Jev-powered router for models, tools, and subagents.
github.comBillionsBobby/JevRouterПодробнее о проекте ↗Source-linked curation
Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter.
github.comoso95/x-scannerПодробнее о проекте ↗Source-linked curation
Calibrated alignment verifier for LLM responses and agent plans — powered by Jev.
github.comcaiovicentino/jev-alignПодробнее о проекте ↗Source-linked curation
Real-time firewall for AI coding agents: a PreToolUse hook checks every Claude Code / Codex tool call with deterministic shell-aware rules, and unmatched actions go to Jev for a calibrated allow/ask/block that fails closed.
github.comKoushik890/jev-firewallПодробнее о проекте ↗Source-linked curation
Tutorial covers API setup and building prototypes with Jev and LLMs.
YouTube · Подробнее о проектеSource-linked curation
Daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill.
Source-linked curation
Предложить ссылку
English
한국어
日本語
Español
Français
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
4 HIGHLIGHTS
Агенты и браузеры
Source-linked curation
ОФИЦИАЛЬНО