Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
A public registry · independent & community-run
Explore the Jev ecosystem.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Watch & learn
Video guides.
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
Experiments.
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.
The directory03 / 03 · Experiments
Find something worth exploring.
Every category, from games and tools to repositories and writeups, traced to a primary source.
Same ideas.
Different paths.
This is the full registry, not just the featured picks. Figures like speed, cost, and stars are maker-reported or captured snapshots, not JevMade measurements.
1613 experiments · showing 1381–1440
Dopamyn uses Jev to tag crypto accounts in a faster version of its existing workflow.
ACTUAL RECORDING12 SEC ↗
Marcel Pociot’s macOS app watches Downloads and uses Jev rules to rename and route files such as invoices.
SOURCE SCREENSHOTEXPAND ↗
Drape lets Jev read speech and the wearer’s current outfit, pick from a closet and change the look in real time.
ACTUAL RECORDING12 SEC ↗
Raptor puts Jev in the decision layer of a dual-arm robot while code handles inverse kinematics and physics.
ACTUAL RECORDING11 SEC ↗
Oskar is building an open-source framework that uses agents and Jev to run end-to-end tests across web and mobile.
ACTUAL RECORDING12 SEC ↗
Jason Torres uses Jev as a multi-purpose router, filter and intent judge before his chatbot calls tools.
SOURCE SCREENSHOTEXPAND ↗
Emogee is a public Jev demo shared by Justin Youens after he could not find a link for the original example.
SOURCE SCREENSHOTEXPAND ↗
Hamed Valigholizadeh asks Jev to rank practice questions by how likely they are to return on a real exam.
ACTUAL RECORDING12 SEC ↗
A family-only LINE bot verifies IDs, uses Jev for classification and controls lights and air conditioning through chat.
SOURCE SCREENSHOTEXPAND ↗
Ackerman’s feed filter asks Jev four binary questions about every post before deciding what reaches the reader.
ACTUAL RECORDING12 SEC ↗
Zohaib Tanwir built a Jev email classifier and tested it from India against a US-hosted endpoint.
SOURCE SCREENSHOTEXPAND ↗
A fraud pipeline lets Jev classify emails quickly, then sends uncertain cases to Kimi K3.
ACTUAL RECORDING12 SEC ↗
Frevana uses Jev to score and cluster top TikTok ads across a chosen category.
SOURCE SCREENSHOTEXPAND ↗
Aditya Singh wired a microphone to Fusion 360, with Jev deciding whether each utterance is a command.
ACTUAL RECORDING12 SEC ↗
内田勉 built an ultra-fast futsal simulator with Jev and Laya for a generative-AI exhibition.
SOURCE SCREENSHOTEXPAND ↗
After a study group on Jev and agent harnesses, たてこ built a werewolf game with the model.
SOURCE SCREENSHOTEXPAND ↗
Ghostfeed uses Jev and Gemini to make a library of reaction videos searchable by structure, reaction and who appears.
ACTUAL RECORDING12 SEC ↗
Nader Dabit demonstrates Jev-powered intent search over Gmail, with semantic retrieval suggested as a first pass for huge inboxes.
SOURCE SCREENSHOTEXPAND ↗
Chris Adcock wired Jev into Grok Bot so bots can drive a real Chrome instance instead of relying on look-and-click.
SOURCE SCREENSHOTEXPAND ↗
Mnimiy’s copy-trading bot uses Jev and Grok Bot to evaluate watched-wallet moves before copying a buy.
ACTUAL RECORDING12 SEC ↗
grok-jev-reflex is an open-source router where Grok plans and acts while Jev handles cheaper yes-or-no decisions between steps.
SOURCE SCREENSHOTEXPAND ↗
RazeDen’s workflow has Jev ask six questions before Grok opens selected material for a campaign.
ACTUAL RECORDING12 SEC ↗
Phil Dressler staged a GTA-style fighter-jet competition with agents built by Astra and controlled by Jev.
ACTUAL RECORDING12 SEC ↗
A Jev-powered headless Chromium agent follows hyperlinks through Wikipedia, demonstrated by navigating outward from the page for coffee.
ACTUAL RECORDING12 SEC ↗
Higgsfield uses Jev to filter content and select assets before DeepSeek and Higgsfield turn them into ad creatives.
ACTUAL RECORDING12 SEC ↗
Hover Explanations uses Jev to reveal contextual explanations, with its maker reporting about $0.006 for the demo test.
ACTUAL RECORDING12 SEC ↗
Vogel tested Jev by classifying 1,500 personal emails and reported being impressed by the results.
SOURCE SCREENSHOTEXPAND ↗
Florian Darroman compares Jev and Fable 5.1 on a post-scheduler build task and reports Jev finishing work faster.
ACTUAL RECORDING12 SEC ↗
Ishwar demonstrates instant Jev compaction during a long Claude Code server-redeployment session.
SOURCE SCREENSHOTEXPAND ↗
iagolast uses Jev to review a company’s invoices and classify them for accounting in seconds.
SOURCE SCREENSHOTEXPAND ↗
Find billing pages with Jev, then list or download invoices—including those in Stripe portals—with one click.
ACTUAL RECORDING12 SEC ↗
Gustav Ekerot demonstrates a Jev-powered interface that assigns tags automatically.
SOURCE SCREENSHOTEXPAND ↗
WOLF backtests a Jev trading setup and reports better results after removing time data and most technical inputs.
SOURCE SCREENSHOTEXPAND ↗
Action Gate asks Jev to score risky agent actions and routes a simulated $50,000 transfer to human review.
ACTUAL RECORDING12 SEC ↗
Give jev-browser a site and task; it opens the browser and lets Jev choose each click from the visible page.
ACTUAL RECORDING12 SEC ↗
JevBest collects Jev demos so visitors can watch each build and find its original post.
ACTUAL RECORDING12 SEC ↗
Jev Calc is Kitze’s smart calculator notebook for working through free-form calculations.
ACTUAL RECORDING12 SEC ↗
Prasad Pilla’s team built an internal Jev candidate qualifier, while warning that recruiting cannot fit neatly into one rubric.
SOURCE SCREENSHOTEXPAND ↗
Dario Crespo puts Jev behind a no-install, no-registration chat and shares the implementation as open source.
SOURCE SCREENSHOTEXPAND ↗
Jev Detector scans text for AI slop without sign-up; its maker reports processing roughly 10,000 words in two seconds.
ACTUAL RECORDING12 SEC ↗
Jevの扉 lets people create and upload genres, with WebMCP support so an agent can make them too.
SOURCE SCREENSHOTEXPAND ↗
Lahiri scores each five-second educational-video segment for relevance, usefulness, importance, memorability, and actionability with Jev.
ACTUAL RECORDING12 SEC ↗
Dorian Smiley reports exhausting $5 of free Jev credit only after processing 123 million tokens.
SOURCE SCREENSHOTEXPAND ↗
JevedIn is Akshat’s LinkedIn extension that uses Jev to detect and block AI slop in the feed.
ACTUAL RECORDING12 SEC ↗
New API exposes Jev’s Choice, Score, and Noul decisions through its gateway and the TypeSafe SDK.
SOURCE SCREENSHOTEXPAND ↗
Kai’s crawler starts at company homepages, finds careers pages, and selects jobs matching a profile.
ACTUAL RECORDING12 SEC ↗
Arthur Marques pits Jev against Laya after narrowing each chess position to ten tactical candidate moves.
ACTUAL RECORDING12 SEC ↗
Thinh Le lets Jev and Laya control a simple Flappy Bird game side by side.
ACTUAL RECORDING12 SEC ↗
Edwin Mesa tests Jev and Laya selecting support documents while a customer is still typing.
SOURCE SCREENSHOTEXPAND ↗
Dorian Smiley tests whether Jev can predict a program’s next state from its current partial state.
SOURCE SCREENSHOTEXPAND ↗
B.AI offers Jev through its API for typed, probabilistic decisions over application state.
SOURCE SCREENSHOTEXPAND ↗
MindsHub added Jev’s decision API to its free tier.
SOURCE SCREENSHOTEXPAND ↗
Chandramouly Kandachar uses Jev to control two virtual hands and their fingers from a piano note waterfall in real time.
ACTUAL RECORDING12 SEC ↗
TypeSafe AI shows Jev steering Doom at roughly ten decisions per second.
ACTUAL RECORDING12 SEC ↗
Izzuddin built a Jev harness for Pokémon Showdown and published a saved match with decisions and latency.
ACTUAL RECORDING12 SEC ↗
Hiroyuki Ota has Jev choose a Puyo Puyo phase and the best resulting board from candidate placements.
SOURCE SCREENSHOTEXPAND ↗
Alan Daitch puts Jev through a high-difficulty Tetris run, with the model choosing every placement.
ACTUAL RECORDING12 SEC ↗
Frank Chen built a small demonstration to probe how Jev behaves under prompt injection.
ACTUAL RECORDING12 SEC ↗
Chat with Jev exposes a question API alongside a ten-hour livestream of the service.
SOURCE SCREENSHOTEXPAND ↗
jev-ranker adds Jev-powered reranking and relevance filtering to retrieval pipelines.
SOURCE SCREENSHOTEXPAND ↗
Jev, briefly
A decision model, not a chatbot.
A chat model generates text token by token and hopes you parse it. Jev never generates a word. Your code sends the state of the world plus typed questions; Jev returns every answer in one parallel pass — typed values with calibrated probabilities and a confidence score your code can trust. About 70–500 ms end to end, $0.042 per million input tokens, output free. Trained with what TypeSafe calls Reinforcement Learning for Calibrated Decisions.
choice Pick one of these.
You define the options. Jev returns the chosen option, a probability for every option, and a confidence. The workhorse of routing, agents, and games — the answer space is always legal, so there is nothing to parse and nothing to hallucinate.
score Rate this on a rubric.
You describe ordered levels — say trivial / normal / critical. Jev returns the level, the probability of each, and a confidence. Scores turn fuzzy judgment (“how severe is this log line?”) into a number-free decision your code can branch on.
noul Is this statement true?
You assert a statement; Jev returns the probability that it is true — a noul. Moderation, verification, guardrails, “does this diff actually fix the bug?”: one question, one calibrated probability.
Official material lives at typesafe.ai and docs.typesafe.ai. JevMade is an independent community registry — not affiliated with or endorsed by TypeSafe AI.
Recurring lessons
Patterns that keep showing up.
One decision per tick
Games, drones, trading bots, and browser agents all converge on the same loop: serialize the state, ask one decisive question, act, repeat. Jev’s latency makes the loop feel instant — the model lives inside the control loop, not outside it.
Confidence as a gate
The answer says what; the confidence says whether to act. The most reliable entries threshold on confidence to route edge cases to a slower model or a human — automation with an honest escape hatch.
Shrink the choice space in code
Makers rarely ask Jev to pick from everything. Local tactics prune 225 gomoku moves to ~40; DOM filters turn a page into an element table; code narrows options, Jev judges within them.
Jev judges, LLMs talk
A recurring split: Jev makes every decision cheaply and instantly, and a small LLM is only invoked when a human-facing string must actually be written. Decision and generation are separate budgets.
Made something with Jev?
Send the link — repo, live demo, post, or video — plus a line on what it does and which primitives it uses. Every entry is verified against its primary source before it ships.
Submit your experiment → hello@JevMade.com