User repository on GitHub
Jev AI quickstart & FAQ — TypeSafe AI's System One model. Try it free: jevtypesafeai.com
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
CommunityJev Demos & Experiments
Jev AI
Community quickstart and FAQ that explains Jev as a called-by-software System One model returning choice, score, or yes-no probability over one API call.
- Stars
- 5
- Published by
- Community
- Author
- codaaiteam
- Last verified
- Oct 2026
About this project
A short, friendly starting point for Jev, the AI model from TypeSafe AI that answers with typed, calibrated decisions instead of text — so software can act on the output directly. Community-maintained, not affiliated with TypeSafe AI. Official site: typesafe.ai. Jev is not a chatbot. It's a System One model built to be called by other software. You send it context + questions; it returns a choice, a score, or a yes/no probability. It can't hallucinate a format — the answer type is fixed by your request.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- Frames Jev as a model called by software, not a chatbot, with typed decisions for automation.
- Documents three answer types: choice among options, ordered score, and calibrated yes-no probability.
- Shows one-POST usage with state plus questions across curl, Python, and TypeScript guides.
- Notes input-only pricing with free output and a free browser playground for first calls.
Watch out
Community-maintained quickstart and FAQ, not affiliated with TypeSafe; confirm behavior in the official docs before building. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
LLMs write prose for people to read. Jev returns a fixed-type value with probabilities for code to branch on, which is why the guide frames it as faster, cheaper, and safe to act on directly.
One POST with a state plus questions. Choice picks among labeled options, score places input on an ordered scale, and noul returns a calibrated yes-no probability, with output tokens free.
It cannot drift format because the answer type is fixed by your request. That removes a class of parsing failures, though you still own thresholds and what each probability means for action.
Yes through the linked free playground, which runs real API calls in the browser. The repo also links separate pages for the explainer, API guide, and pricing rather than repeating them.
choice picks one of up to 255 labelled options and returns probabilities; score places the input on a 2 to 10 level ordered scale; noul returns a calibrated yes/no as a probability from 0 to 1. Routing and classification use choice, risk and quality use score, and gates use noul.
$0.042 per million input tokens with output free, roughly $0.0004 per decision, and it answers in about 70 to 500 ms. Input-only billing means you optimize question design rather than completion length.
TypeSafe AI, founded by ex-OpenAI researcher Diogo Almeida and launched in September 2026 with $40M seed. This quickstart is community-maintained and not affiliated with TypeSafe, and the names Jev, System One and TypeSafe AI belong to their respective owners.
More Jev resources like this
46GitHub stars
Open 150M encoder that reproduces the typed noul, choice, and score interface in one forward pass, trainable on a free GPU and runnable locally for nothing.
Jev Demos & Experiments#community#jevbest#catalog-import
941GitHub stars
Library that adds schema-guaranteed typed outputs to existing autoregressive LLMs without changing weights, served through SGLang or a hosted API.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
TypeLLM/TypeLLMPython
TypeLLM/TypeLLMPython98GitHub stars
Self-hosted Docker service and web UI that packages Laya structured-decision inference behind a compatible System One endpoint.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
1Panel-dev/laya-serverPython
1Panel-dev/laya-serverPython39GitHub stars
Community Spring Boot starter that injects a JevClient into Spring MVC apps to ask typed noul, choice, and score questions against the TypeSafe API.
Jev Demos & Experiments#community#awesomejev#catalog-import
Community
danvega/jev-spring-boot-starterJava
danvega/jev-spring-boot-starterJava39GitHub stars
Mac menu-bar voice controller where Jev picks the next action from observed Accessibility controls and Swift executes it in an observe-decide-execute loop.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
ronadin2002/jev-cuaSwift
ronadin2002/jev-cuaSwift55GitHub stars
Toolkit that makes a model behind an OpenAI-compatible endpoint or running in-process answer typed choice, score, and yes/no questions from next-token probabilities in Jev API shape.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
fidecastro/jevifyPython
fidecastro/jevifyPythonFrom the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.