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.
1612 experiments · showing 781–840
A record of five attempts to find a worthwhile job for Jev—and the reasons each stayed out of production.
SOURCE SCREENSHOTEXPAND ↗
from the source
const r = await client.systemOne({ state: { command }, questions: { harm: noul(question) }, ...(model ? { model } : {}), });
A Magic 8-Ball with twenty custom replies, from “Yes. Stop asking.” to “You already know. You just wanted a witness.”
ACTUAL RECORDING12 SEC ↗
choice
You are a super intelligent and witty magic 8-ball. Choose the best answer to reply to the user’s question. · Yes. Stop asking. / Ask a human with a l...
A pull-request Magic 8-Ball that turns nine GitHub signals into one of four light-review verdicts without approving anything.
SOURCE SCREENSHOTEXPAND ↗
choice
The question is whether this pull request can be approved on a light read, without studying the code. · yes / lean_yes / unclear / no
Read a novel with sentence-by-sentence emotion highlights and a whole-book character map beside the page.
SOURCE SCREENSHOTEXPAND ↗
Search a site immediately, then watch Jev rerank the top twenty lexical matches as its judgments arrive.
SOURCE SCREENSHOTEXPAND ↗
Give a browser agent a task and watch Jev choose each click from the page’s observed controls.
SOURCE SCREENSHOTEXPAND ↗
Turn a 3D Rubik’s Cube yourself while Jev decides when to coach you, stay quiet, or offer a demonstration.
SOURCE SCREENSHOTEXPAND ↗
Applies a YAML policy to Claude Code tool calls, using Jev scores to allow, deny, or review each action.
SOURCE SCREENSHOTEXPAND ↗
Ranks Clay people-search results with Jev probabilities for role fit and current operating-founder status.
SOURCE SCREENSHOTEXPAND ↗
Composes Unix-style tools that seed, expand, judge, verify, and report code defects while preserving evidence chains.
SOURCE SCREENSHOTEXPAND ↗
Routes each agent turn’s effort, tools, skill, and model tier from one bounded Jev request behind a hard deadline.
SOURCE SCREENSHOTEXPAND ↗
Reorders visible Gmail rows by unread status, criticality, urgency, and user-defined labels without changing messages in Gmail.
SOURCE SCREENSHOTEXPAND ↗
Turns an agent skill into project-specific Oxlint checks, using AST rules for structure and Jev for contextual judgement.
SOURCE SCREENSHOTEXPAND ↗
Adds a zero-dependency CLI and coding-agent skill for batching narrow yes/no, choice, and score judgements.
SOURCE SCREENSHOTEXPAND ↗
Enter a Korean name and see Jev choose the most likely age band for it in a small React experiment.
SOURCE SCREENSHOTEXPAND ↗
Give agents local MCP tools for versioned Jev question packs and custom typed judgments, using each operator's own TypeSafe key.
SOURCE SCREENSHOTEXPAND ↗
Hover text in Chrome or Firefox to see Jev answer configurable questions as colored outlines and probability cards.
ACTUAL RECORDING12 SEC ↗
Switchloom experiments with Jev-routed persistent coding agents and publishes pilots where routing failed to beat a single Astra model.
SOURCE SCREENSHOTEXPAND ↗
Turn natural-language commands into allowlisted tinystruct actions while preserving enum, boolean, and verbatim input arguments.
SOURCE SCREENSHOTEXPAND ↗
Group repeated server errors into incidents, route actionable cases with Jev, and keep fixes open until verification holds.
SOURCE SCREENSHOTEXPAND ↗
Open Jev assessment tabs in Magento to inspect judgments about orders, customers, products, reviews, and abandoned carts.
SOURCE SCREENSHOTEXPAND ↗
TypeSafe AI
officialTypeSafe AI builds models that make fast, structured decisions inside software.
SOURCE SCREENSHOTEXPAND ↗
Documentation
officialThe official documentation explains how to send state and typed questions to Jev.
SOURCE SCREENSHOTEXPAND ↗
Quick start
officialA concise guide to making your first Jev request.
SOURCE SCREENSHOTEXPAND ↗
Playground
officialAn interactive playground for trying TypeSafe models.
SOURCE SCREENSHOTEXPAND ↗
HTTP API reference
officialThe complete HTTP API reference for TypeSafe's evaluation endpoint.
SOURCE SCREENSHOTEXPAND ↗
Primitives
officialA guide to Jev's Choice, Score, and Noul question types and their answers.
SOURCE SCREENSHOTEXPAND ↗
Patterns
officialArchitectural patterns for incorporating TypeSafe decisions into software.
SOURCE SCREENSHOTEXPAND ↗
Cookbooks
officialTypeSafe's recipes for asking Jev several questions in one call.
SOURCE SCREENSHOTEXPAND ↗
Smart home demo
officialA smart-home assistant demo that uses TypeSafe to evaluate user requests.
SOURCE SCREENSHOTEXPAND ↗
Workflow evals
officialResources for evaluating workflows built with TypeSafe.
SOURCE SCREENSHOTEXPAND ↗
Jev 1.13 jaggedness
officialA candid guide to the known limitations and rough edges in Jev 1.13.
SOURCE SCREENSHOTEXPAND ↗
TypeSafe introduces System One models and its first model, Jev.
SOURCE SCREENSHOTEXPAND ↗
Manifesto
officialTypeSafe argues that AI belongs inside everyday software, making small decisions rather than chatting with a person.
SOURCE SCREENSHOTEXPAND ↗
Ask Jev to make a decision from Python, or plug in your own model.
SOURCE SCREENSHOTEXPAND ↗
from the source
from decido import Choice, SyncSessionfrom decido.providers.typesafe import TypeSafeProvidersession = SyncSession(TypeSafeProvider()).start()result = session.decide( state="Every API call fails after our signing-key rotation.",
A Rust client for TypeSafe's Jev System One API.
SOURCE SCREENSHOTEXPAND ↗
choice
Which team should handle this?
A typed Rust layer for Jev's Choice, Score, and Noul primitives.
SOURCE SCREENSHOTEXPAND ↗
A small Rust client for integrating TypeSafe's Jev model.
SOURCE SCREENSHOTEXPAND ↗
from the source
The API key is read from `TYPESAFE_API_KEY` or supplied to `ClientConfig`. It isredacted from `Debug` and never included in errors. The live example spends areal API call:
An idiomatic Elixir client for the TypeSafe AI API.
SOURCE SCREENSHOTEXPAND ↗
score
How frustrated is the customer?
An Elixir client for TypeSafe AI with typed responses and bounded concurrency.
SOURCE SCREENSHOTEXPAND ↗
An Elixir client for Jev with offline test stubs and concurrent request fan-out.
SOURCE SCREENSHOTEXPAND ↗
An Elixir SDK for TypeSafe AI built with Req.
SOURCE SCREENSHOTEXPAND ↗
A latency-focused Rust SDK for TypeSafe's System One API.
SOURCE SCREENSHOTEXPAND ↗
A PHP and Laravel SDK for TypeSafe AI's Jev models.
SOURCE SCREENSHOTEXPAND ↗
score
How urgent is this ticket?
An unofficial Go SDK designed to match the official JavaScript and Python TypeSafe SDKs.
SOURCE SCREENSHOTEXPAND ↗
from the source
resp, err := client.SystemOne(ctx, req)if err != nil { var rateLimit *typesafe.RateLimitError var apiErr *typesafe.APIError switch {
An unofficial PHP SDK designed to match the official JavaScript and Python TypeSafe SDKs.
SOURCE SCREENSHOTEXPAND ↗
from the source
<?phpdeclare(strict_types=1);use TypeSafe\Choice;use TypeSafe\Client;$client = new Client();
An idiomatic Zig client for the TypeSafe AI API.
SOURCE SCREENSHOTEXPAND ↗
from the source
// build.zigconst typesafe = b.dependency("typesafe", .{ .target = target, .optimize = optimize });exe.root_module.addImport("typesafe", typesafe.module("typesafe"));
A Vercel AI Gateway page for trying TypeSafe's Jev model.
SOURCE SCREENSHOTEXPAND ↗
An adapter that connects Jev to Mellea.
SOURCE SCREENSHOTEXPAND ↗
Bring Jev into an n8n workflow to answer yes-or-no questions, choose an option or give a score.
SOURCE SCREENSHOTEXPAND ↗
A TrainLCD contribution that adds Jev-based reranking to its Functions workers.
SOURCE SCREENSHOTEXPAND ↗
Reusable shadcn-style interface components and blocks for TypeSafe AI applications.
SOURCE SCREENSHOTEXPAND ↗
Call TypeSafe's decision models through the Vercel AI SDK.
SOURCE SCREENSHOTEXPAND ↗
Let a coding agent fix a GitHub issue, with tests and AI reviewers checking its work before it proceeds.
SOURCE SCREENSHOTEXPAND ↗
An experiment in checking an agent's work before handing it to another agent, with Jev helping review the evidence.
SOURCE SCREENSHOTEXPAND ↗
A CLI and GitHub Action that combines deterministic rules with Jev to assess the risk of code changes.
SOURCE SCREENSHOTEXPAND ↗
from the source
- uses: moezubair/check-risk@v0.1 with: base: ${{ github.event.pull_request.base.sha }} head: ${{ github.event.pull_request.head.sha }} typesafe-api-key: ${{ secrets.TYPESAFE_API_KEY }}
A configurable Go CLI that uses Jev to route prompts between models.
SOURCE SCREENSHOTEXPAND ↗
An experimental Hermes plugin for planning model routes within budget and capability constraints.
SOURCE SCREENSHOTEXPAND ↗
from the source
hermes plugins install ussyverse/hermes-jev-router --no-enable# Review code, then enable explicitly:hermes plugins enable jev-router
A Grok skill that combines Jev probabilities with prior beliefs to choose the next action in a builder-agent loop.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/rainbowpuffpuff/jev-builder-loop.gitmkdir -p ~/.grok/skillsln -sfn "$(pwd)/jev-builder-loop" ~/.grok/skills/jev-builder-loop
An automated pull-request reviewer with Jev-based approval thresholds and escalation to trusted owners.
SOURCE SCREENSHOTEXPAND ↗
from the source
export TYPESAFE_API_KEY='...'export GITHUB_TOKEN='...'.venv/bin/python -m jev_review github --repo OWNER/REPO --pr 123 --config examples/githu....venv/bin/python -m jev_review poll --repo OWNER/REPO --config examples/github-config.js...
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