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.
JEVLAB ARTTypeSafe 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.
JEVLAB ARTStart with the Launch Post. Explore four official signals.
1,198 resources
AI-assisted summaries and translations. Check original sources for context and performance claims.
vogelA system tested on 1,500 emails for classification effectiveness. Demonstrates potential for automated email management.
EnglishSource-linked curation
Jason LuA tool that improves end-to-end testing efficiency, completing tasks faster and cheaper than other models.
EnglishSource-linked curation
Max BladeJev plays Subway Surfers at superhuman speed and handles 50 games simultaneously for under a cent.
EnglishSource-linked curation
Using Jev to create Clay workflows instantly, leveraging its capabilities for rapid development.
JEVLAB ARTEnglishSource-linked curation
A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard.
JEVLAB ARTEnglishSource-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.
JEVLAB ARTEnglishSource-linked curation
Alan DaitchJev AI plays Tetris at high speed, completing 357 pieces and 134 lines in 2 minutes. Demonstrates rapid decision-making capabilities.
EspañolSource-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.
JEVLAB ARTEnglishSource-linked curation
Local A-share technical analysis using Jev Choice and Noul questions to assess direction and volatility across two horizons, with evidence for Buy/Hold/Sell assessments and no order execution.
JEVLAB ARTEnglishSource-linked curation
A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.
JEVLAB ARTEnglishSource-linked curation
Fazt presenta las decisiones estructuradas de Jev con ejemplos de Snake y clasificación de solicitudes de soporte.
EspañolSource-linked curation
Jev predicts upcoming shell commands by analyzing historical command data.
JEVLAB ARTEnglishSource-linked curation
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz.
JEVLAB ARTEnglishSource-linked curation
A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.
JEVLAB ARTEnglishSource-linked curation
Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good).
JEVLAB ARTEnglishSource-linked curation
Browser automation with Jev (TypeSafe) as decision model.
JEVLAB ARTEnglishSource-linked curation
Video comparison against a structured-output LLM baseline.
JEVLAB ARTEnglishSource-linked curation
22 Jev models, one ball: a 3D football match where every player is its own Jev (TypeSafe AI System One) decision. Watch, or take over the number 9.
JEVLAB ARTEnglishSource-linked curation
A user tested the new Jev model and shared insights about its significance for System One models.
EnglishSource-linked curation
Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.
JEVLAB ARTEnglishSource-linked curation
MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer.
JEVLAB ARTEnglishSource-linked curation
OFFICIALTypeSafe AIOfficial TypeSafe reference: Legal.
JEVLAB ARTEnglishSource-linked curation
TrustGate — indie media T&S gate via TypeSafe Jev.
JEVLAB ARTEnglishSource-linked curation
Agentcard integrates Jev and Kernel to enable secure and efficient online shopping by agents, avoiding token costs and safety issues.
JEVLAB ARTEnglishSource-linked curation
An optimized inference engine to turn LLMs into Jev-like machines: optimized for quick, lightweight, and accurate decision-making, classification, and scoring.
JEVLAB ARTEnglishSource-linked curation
Starchild uses Jev for real-time prompt classification, reducing costs by 20x and increasing speed by 6x with average processing time of 140ms.
JEVLAB ARTEnglishSource-linked curation
Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.
JEVLAB ARTEnglishSource-linked curation
omar ✌️A system that quickly captures user interface flows on demand, enabled by Jev's fast processing capabilities.
EnglishSource-linked curation
Open-source BYOK arena for Jev and other AI judges. Find failures, compare quality, cost, and latency.
JEVLAB ARTEnglishSource-linked curation
OFFICIALTypeSafe AIOfficial TypeSafe reference: State.
JEVLAB ARTEnglishSource-linked curation
A developer project using Jev to play Pokémon Red by typing each turn.
JEVLAB ARTEnglishSource-linked curation
A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.
JEVLAB ARTEnglishSource-linked curation
OskarFramework for running end-to-end tests with agents using Jev.
EnglishSource-linked curation
TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.
JEVLAB ARTEnglishSource-linked curation
Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
JEVLAB ARTEnglishSource-linked curation
A community experiment demonstrating Jev's interaction with a video game.
JEVLAB ARTEnglishSource-linked curation
Jack ChengA tool that uses Jev to convert pointing and speech into drawing actions on a canvas.
EnglishSource-linked curation
Autonomous System-One Triage Engine & Benchmark powered by TypeSafe AI (Jev). 75ms inference, $0 output tokens, and RLCD epistemic safety gates.
JEVLAB ARTEnglishSource-linked curation
Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM.
JEVLAB ARTEnglishSource-linked curation
A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
JEVLAB ARTEnglishSource-linked curation
OFFICIALTypeSafe AIOfficial TypeSafe reference: Pre-parsed value extraction.
JEVLAB ARTEnglishSource-linked curation
Typed, confidence-aware agent skill routing with TypeSafe Jev.
JEVLAB ARTEnglishSource-linked curation
Alex NikolicAn MLP trained on Qwen 4B that functions similarly to Jev, offering a typesafe alternative.
EnglishSource-linked curation
Typesafe's jev as a "fuzzy linter". give your code an ocular patdown.
JEVLAB ARTEnglishSource-linked curation
弈瞬：双 Jev 五子棋九宫格输入实验台，逐手查看模型决策，支持真实对局回放与实时对战。
JEVLAB ARTEnglishSource-linked curation
Jev as an LLM prompt guardrail inside the agentgateway proxy, with tracing and cost tracking.
JEVLAB ARTEnglishSource-linked curation
A community post suggesting Jev can be hired as a QA tester through @typesafeai.
JEVLAB ARTEnglishSource-linked curation
A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse.
JEVLAB ARTEnglishSource-linked curation
A community post describes Jev attempting to play Resident Evil, testing its ability to handle 3D environments, objectives, and combat scenarios.
JEVLAB ARTEnglishSource-linked curation
Openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド.
JEVLAB ARTEnglishSource-linked curation
A developer project offering 110 interactive use cases, games, and scenarios with editable prompts.
JEVLAB ARTEnglishSource-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.
JEVLAB ARTEnglishSource-linked curation
Evidence-backed use cases, patterns, and guidance for building with Jev, TypeSafe AI's System One model. Every claim is labeled and sourced.
JEVLAB ARTEnglishSource-linked curation
3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.
JEVLAB ARTEnglishSource-linked curation
Match user goals to MCP catalog (two-stage) via TypeSafe Jev.
JEVLAB ARTEnglishSource-linked curation
khaledDemonstration of Jev's capability for rapid variable generation in development workflows.
EnglishSource-linked curation
SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded.
JEVLAB ARTEnglishSource-linked curation
DuncanEphraim Duncan's demo where Jev decides which model should serve a request.
EnglishSource-linked curation
A developer project that selects applicable rules for Claude, ensuring only relevant information is shown.
JEVLAB ARTEnglishSource-linked curation
A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
JEVLAB ARTEnglishSource-linked curation
A tool for tracking decisions made by Jev, using Arize's instrumentation for detailed analysis.
JEVLAB ARTEnglishSource-linked curation
Voice command integration for the Autumn billing dashboard to streamline tasks.
JEVLAB ARTEnglishSource-linked curation
One direct Jev question per row against 12–14 Jev-scored dimensions with locally fitted weights on three classification tasks: 5,477 test rows, 25,174 Jev calls, $1.43. Decomposition wins on Japanese NLI (0.9076 vs 0.8373) but flags about 25× more hard benign rows as attacks (37.2% vs 1.5%).
JEVLAB ARTEnglishSource-linked curation
Brood War in WASM exposed as an MCP server, with Jev playing and still losing to a Zerg rush.
JEVLAB ARTEnglishSource-linked curation
Matched-precision comparison against a private fine-tuned classifier.
JEVLAB ARTEnglishSource-linked curation
A SillyTavern extension that evaluates replies before they are displayed, collected for the creative shelf.
JEVLAB ARTEnglishSource-linked curation
Job Risk Analyzer: CLI and REST API that uses Jev to score an occupation's exposure to AI-driven layoffs and its resilience.
JEVLAB ARTEnglishSource-linked curation
Using the new model JEV to play the game tetris.
JEVLAB ARTEnglishSource-linked curation
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
JEVLAB ARTEnglishSource-linked curation
Pre-install security gate for npm lifecycle scripts using TypeSafe System One.
JEVLAB ARTEnglishSource-linked curation
Unofficial go sdk for typesafe ai.
JEVLAB ARTEnglishSource-linked curation
A game project involving a penalty shootout against Jev using Render Workflows and Postgres.
JEVLAB ARTEnglishSource-linked curation
Submit a find
한국어
日本語
Français
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
Decisions & routing
Source-linked curation
Tools & apps
Games & real time
Agents & browsers
Research & data
Markets & experiments
Creative & growth