Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Read & learn
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Watch & learn
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.

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.
393 experiments · showing 61–120
Compose Jev state and typed questions in a visual IDE, inspect the request JSON, then explore probability-rich result cards.
Keep what you find. Notes stay private.
Open a Markdown vault as a matrix of notes and tags, then review Jev’s colored confidence nodes before writing frontmatter.
Keep what you find. Notes stay private.
A tiny workflow language where conditions such as “this email feels urgent” resolve to Jev probabilities.
Keep what you find. Notes stay private.
Shortlists local Markdown passages lexically, reranks them with Jev, and returns original text with source references intact.
Keep what you find. Notes stay private.
Paste a message to see how it sounds before sending, from overall tone to sarcasm, urgency, pushiness, and formality.
Keep what you find. Notes stay private.
An OpenTelemetry log-triage tool that uses Jev to decide which signals warrant deeper language-model analysis.
Keep what you find. Notes stay private.
A stock dashboard that uses Jev to classify and score daily market conditions.
Keep what you find. Notes stay private.
Edit Jev scenarios beside their typed answers and probabilities in a colorful three-column playground.
Keep what you find. Notes stay private.
A live Hyperliquid trading application that can use Jev as its decision model.
Keep what you find. Notes stay private.
A UI experiment that asks Jev to choose layouts and components for working shadcn screens.
Keep what you find. Notes stay private.
Moderates tournament copy and in-game snake shouts, while keeping hard blocks and the human review queue firmly in code.
Keep what you find. Notes stay private.
Combines DeepSeek-written WeChat replies with optional Jev intent checks, quality review, and ranking on Windows and preview macOS builds.
Keep what you find. Notes stay private.
Try three editable forms that show how Jev routes each submission to a recipient.
Keep what you find. Notes stay private.
A recursive tournament engine that uses Jev scoring and Swiss matchmaking to rank AI candidates by Elo.
Keep what you find. Notes stay private.
A command-line tool for inserting Jev-based semantic decisions into Unix pipelines and CI jobs.
Keep what you find. Notes stay private.
Turn live Japanese speech into variety-show captions, manga effects, colored lenses, and sound cues.
Keep what you find. Notes stay private.
A book becomes a glowing poster as Jev scores the emotions in its passages.
Keep what you find. Notes stay private.
Browse Taobao or JD while products that may come from non-weekend-friendly workplaces receive a PASS stamp.
Keep what you find. Notes stay private.
Cover YouTube recommendations judged more distracting than useful while keeping a “show anyway” escape hatch.
Keep what you find. Notes stay private.
Describe the icon you need and watch matching SF Symbols rise out of a physics-driven pile.
Keep what you find. Notes stay private.
Blur X posts that match expressions you choose, using Jev scores rather than hiding an entire account.
Keep what you find. Notes stay private.
A shell client for asking Jev Noul, Choice, and Score questions and receiving numeric answers rather than prose.
Keep what you find. Notes stay private.
A playful experiment that makes Jev compose a Grug-style reply one chosen word at a time.
Keep what you find. Notes stay private.
Type an ambiguous Chinese message and compare judgments about its meaning, anger level, and need for a caring response.
Keep what you find. Notes stay private.
Watch Kubernetes pods while Jev labels incident severity, suggests a remediation class, and flags cases for a human.
Keep what you find. Notes stay private.
Triage Gmail at a glance with badges for category, priority, spam likelihood, and whether a message needs a reply.
Keep what you find. Notes stay private.
An ad-free YouTube client whose Windows companion experiments with Jev recommendations and quality selection.
Keep what you find. Notes stay private.
A Rust query language that mixes ordinary analytics with row-by-row semantic judgments from Jev.
Keep what you find. Notes stay private.
Lets people test which memories Jev would admit, comparing editable cases through an inspectable web interface.
Keep what you find. Notes stay private.
Flags OpenAPI changes whose schemas still match but whose descriptions imply different behaviour.
Keep what you find. Notes stay private.
Paste JSON, a JWT, cron, stack trace, code, or prose and watch the page become the tool that content needs.
Keep what you find. Notes stay private.
Let Hermes plan milestones while Jev chooses immediate actions for a Mineflayer bot in Minecraft.
Keep what you find. Notes stay private.
Mark likely sponsor reads on a YouTube seek bar and skip them automatically using judgments made from captions.
Keep what you find. Notes stay private.
Paper-trade live markets with agents that ask Jev once a second whether prices look ready to rise, fall, or stay flat.
Keep what you find. Notes stay private.
A chat assistant for Feishu and WeCom that uses Jev to separate tasks and urgent requests from everyday chatter.
Keep what you find. Notes stay private.
Drop a folder of résumés into a desktop app and compare judgments of role, seniority, technical depth, and possible inflation.
Keep what you find. Notes stay private.
Grade a page separately for search engines, answer engines, and generative-engine citation, then rank evidence-backed fixes.
Keep what you find. Notes stay private.
Give an Android device a goal and let Jev navigate its accessibility tree one tap, swipe or back action at a time.
Keep what you find. Notes stay private.
A terminal oracle that answers any question with a bare Yes or No, then renders the verdict in a 3D hyperspace.
Keep what you find. Notes stay private.
Turns a plain-language request into a macOS menu action by scoring every available menu path with Jev.
Keep what you find. Notes stay private.
Chooses a meal from a personal candidate pool by combining Jev suitability checks with a final bounded choice.
Keep what you find. Notes stay private.
Build a personal Hacker News feed by scoring new stories and articles against interests saved by each reader.
Keep what you find. Notes stay private.
A code-search CLI that asks the same yes-or-no question of every function and ranks the answers.
Keep what you find. Notes stay private.
A small, dependency-free Python CLI for Jev Choice, Score, and Noul questions.
Keep what you find. Notes stay private.
A TypeScript library that recursively navigates a taxonomy so Jev can choose among more than 255 options.
Keep what you find. Notes stay private.
A live tone labeler for Bluesky posts and drafts using Jev.
Keep what you find. Notes stay private.
A SQLite extension for filtering, ranking, classifying, and scoring rows with natural-language predicates evaluated by Jev.
Keep what you find. Notes stay private.
A macOS window switcher that uses Jev to predict which window the user wants next.
Keep what you find. Notes stay private.
Speak through your notes while Jev quietly checks off each talking point once you have covered it.
Keep what you find. Notes stay private.
Sweep through a synthetic inbox as Jev sorts messages, flags required action, and identifies mail that looks safe to trash.
Keep what you find. Notes stay private.
Judge whether an article or video merits a read, skim, save, or skip before you open it.
Keep what you find. Notes stay private.
Press a macOS shortcut, speak a command, and let Jev route it to a bounded app, typing, volume, or interface action.
Keep what you find. Notes stay private.
Type a short phrase and browse a many-emoji reply assembled from Jev's relevance scores.
Keep what you find. Notes stay private.
Tell Tab Bouncer what you are working on, then review and close the open tabs most likely to lead you astray.
Keep what you find. Notes stay private.
Open an Idealista rental and receive an on-page check for scam signals, contract traps, and unusual pricing.
Keep what you find. Notes stay private.
A writing scorecard for spotting filler and unclear prose.
Keep what you find. Notes stay private.
Tell a Chrome side panel what you want done, and it chooses visible controls while watching for completion and risky clicks.
Keep what you find. Notes stay private.
Shows how strongly each Kotlin file follows functional-programming ideas such as immutability, pure functions and explicit effects.
Keep what you find. Notes stay private.
Sorts exported Upwork listings into apply, review or skip for one freelancer's skills and working constraints.
Keep what you find. Notes stay private.
Lints text files with explicit anti-slop rules and Jev judgments, leaving a separate writing agent to make the repairs.
Keep what you find. Notes stay private.
Jev, briefly
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.
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.
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.
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
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.
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.
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.
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.
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 experimentSign in first so we can reply to you. Submissions are reviewed, not published automatically.