Latest addition
Source check
Recent activityA FIELD GUIDE TO JEV / VOL. 01
The best of Jev. Real projects, practical guides and ideas from across the internet.
THE OFFICIAL SIGNAL 4 HIGHLIGHTS
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.
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 everyoneExplore this project ↗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 useExplore this project ↗Start with the Launch Post. Explore four official signals.
378 resources
AI-assisted summaries and translations. Check original sources for context and performance claims.
An experiment using Jev to interpret voice commands and trigger tool actions before the user finishes speaking.
EnglishSource-linked curation
A tested resource evaluating Jev's capabilities in browser automation and support tasks.
EnglishSource-linked curation
Typesafe's jev as a "fuzzy linter". give your code an ocular patdown.
EnglishSource-linked curation
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/siegeExplore this project ↗EnglishSource-linked curation
Jev (System One decision model) plugin suite for DeepSeek Harness (dsh).
github.comzhangxaochen/dsh-jevExplore this project ↗EnglishSource-linked curation
A Codex plugin that uses Jev to streamline and reduce excessive tool outputs.
EnglishSource-linked curation
x.comA community post discusses Jev as a faster general classifier/decision-maker, questioning its accuracy in complex scenarios and noting potential benefits in limited solution spaces with low latency requirements.
x.comDay-one notes from a skeptic, in ChineseExplore this project ↗
简体中文Source-linked curation
Detects low-quality content in real-time as users scroll.
EnglishSource-linked curation
A developer project demonstrates Jev's rapid response to browser tasks, with decisions made in approximately 100 milliseconds.
EnglishSource-linked curation
Interactive TypeScript coding CLI with typed routing, decision programs, and validated formal trees driven by Jev.
github.comrhighs/jev-codeExplore this project ↗EnglishSource-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-approvalsExplore this project ↗EnglishSource-linked curation
Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.
EnglishSource-linked curation
A community post about humor management on a social platform.
EnglishSource-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-evalExplore this project ↗EnglishSource-linked curation
TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.
github.comphyous/tsai-civ2Explore this project ↗EnglishSource-linked curation
Ira BodnarReduces SEO and GEO fix costs by 90% through faster data analysis and automation.
EnglishSource-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-gateExplore this project ↗EnglishSource-linked curation
RomànA community post demonstrating Jev's ability to score 700 leads and predict outreach message performance in 40 seconds.
EnglishSource-linked curation
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
EnglishSource-linked curation
An agent system that makes one Jev decision per computational step.
EnglishSource-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-socialExplore this project ↗EnglishSource-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-commitExplore this project ↗EnglishSource-linked curation
A community post describing 500 real-time agents operating in a 3D environment with notable performance metrics.
EnglishSource-linked curation
A developer project offering semantic code search for coding agents, benchmarked on SWE-bench Lite.
EnglishSource-linked curation
A developer project integrating Jev for judgment tasks within DeepSeek Harness.
github.comHorusJiang/dsh-jev-toolsExplore this project ↗EnglishSource-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-routerExplore this project ↗EnglishSource-linked curation
tamaraEnables instant compaction by scoring and filtering tool calls efficiently.
EnglishSource-linked curation
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/CannyExplore this project ↗EnglishSource-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-dslExplore this project ↗EnglishSource-linked curation
Mormon NegroAn agent using headless Chromium to quickly navigate the web, demonstrated by browsing Wikipedia links efficiently.
EspañolSource-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 stepsExplore this project ↗Source-linked curation
Aside agents decide with TypeSafe Jev (System One: Choice/Score/Noul). Not a Cua binding — Jev is the model, Aside is the browser runtime.
github.comhimomohi/aside-jevExplore this project ↗EnglishSource-linked curation
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/pijevExplore this project ↗EnglishSource-linked curation
Uses typeful jev, zero sync to pull and sync large repositories for issue triage.
github.comcephalization/jev-triageExplore this project ↗EnglishSource-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.
EnglishSource-linked curation
Idan LevinJev achieved 100% task success on the WebMCP benchmark with significantly lower model costs compared to other systems, using a combination of tool selection and argument generation.
EnglishSource-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.
EnglishSource-linked curation
A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
EnglishSource-linked curation
MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.
EnglishSource-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-hypermemExplore this project ↗EnglishSource-linked curation
Jev-powered semantic browser use.
github.comsightmap/jev-turboExplore this project ↗EnglishSource-linked curation
Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex.
EnglishSource-linked curation
JevArena — two Jev agents duel in click-only browser games (Browser Use + TypeSafe Jev).
github.comraihankhan-rk/jevarenaExplore this project ↗EnglishSource-linked curation
Retriever AI evaluates Jev's performance on real browser tasks, identifying strengths and areas for improvement in integration with larger models.
EnglishSource-linked curation
TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate.
github.comajensenwaud/hermes-jev-pluginExplore this project ↗EnglishSource-linked curation
Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.
github.comshaharia-lab/jev-cliExplore this project ↗EnglishSource-linked curation
Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration.
github.comkomikat/psearchExplore this project ↗EnglishSource-linked curation
Chrome extension that re-ranks Google results with TypeSafe Jev and folds away sales pages and SEO filler.
github.comtylergibbs1/siftExplore this project ↗EnglishSource-linked curation
A browser form for building requests to TypeSafe's Jev: pick a template, fill in the blanks, copy the request. No JSON, no install, runs locally.
github.comcollapseindex/jev-builderExplore this project ↗EnglishSource-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/switchboardExplore this project ↗EnglishSource-linked curation
Chrome extension that triages Gmail with TypeSafe's Jev model: category, priority, spam % and reply % on every email.
github.commuhammedilyasy/jev-mailExplore this project ↗EnglishSource-linked curation
A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model.
github.comscale-venture-partners/riffExplore this project ↗EnglishSource-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 forExplore this project ↗EnglishSource-linked curation
An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.
github.comaltryne/jevifyExplore this project ↗EnglishSource-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-adExplore this project ↗EnglishSource-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/tiershiftExplore this project ↗EnglishSource-linked curation
Self-improving agent harness with an optional TypeSafe Jev companion for typed Choice, Score, and Noul judgments.
github.comwundercorp/lokiExplore this project ↗EnglishSource-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 buildingExplore this project ↗EnglishSource-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-2BExplore this project ↗EnglishSource-linked curation
Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev.
github.comRipwords/agent-gate-loopExplore this project ↗EnglishSource-linked curation
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.
github.comgaborishka/jev-canvasExplore this project ↗EnglishSource-linked curation
Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev.
github.comTheoOliveira/pi-jevExplore this project ↗EnglishSource-linked curation
Jev-powered model-judged permission gate for OMP (TypeSafe System One).
github.comSTRML/omp-jevens-classifierExplore this project ↗EnglishSource-linked curation
Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).
github.comTokenTrim/jev-agent-failure-benchmarkExplore this project ↗EnglishSource-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-scannerExplore this project ↗EnglishSource-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-gatesExplore this project ↗EnglishSource-linked curation
A Jev browser agent implemented in Go, connected to a real Chrome browser for agent-based tasks.
github.comphanngoc/browser-aiExplore this project ↗EnglishSource-linked curation
Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.
github.comIcohen007/jev-play-ping-pongExplore this project ↗EnglishSource-linked curation
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/CheshiExplore this project ↗EnglishSource-linked curation
Using Typesafe.AI to generate diff reviews.
github.comrbalch/typesafeai-reviewExplore this project ↗EnglishSource-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/xtagsExplore this project ↗EnglishSource-linked curation
Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.
github.comarunav25/jev-mcpExplore this project ↗EnglishSource-linked curation
Submit a find
한국어
日本語
Français
Deutsch
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
Agents & browsers
Source-linked curation
