Skip to content
JevDirectory.org
CommunityCookbooks & Demos3 starsVerified 2026-09-22

Soupbase

A Chinese and English lateral-thinking puzzle site hosted by Jev: Choice questions classify player questions and check proposed solutions against required facts, while code enforces confidence thresholds before a puzzle is marked solved.

Open github.comspoonnotfound/soupbase
Category
Cookbooks & Demos
Published by
Community
Author
spoonnotfound
Added
2026-09-22
Tagscommunitytypescriptgamesvercelpostgres

Highlights

  • Jev answers with four host verdicts - yes, no, not important, and cannot judge yet - and the site shows the model's native confidence.
  • Calls go through the Vercel AI Gateway as typesafe-ai/jev, and results return structured options, probabilities, and confidence.
  • Ships 50 stories in both Chinese and English, 100 JSON files: 14 beginner, 25 standard, and 11 advanced puzzles.
  • Supports BYOK, a deployment-provided key, or both via AI_ACCESS_MODE, and web-created puzzles stay private with revocable share links.
  • Tests use an isolated database and simulated models, need no real key, and cover access control, share revocation, version pinning, and credential isolation.

Quickstart

bash
npm ci
cp .env.example .env.local
npm run content:sync
npm run dev   # open http://localhost:3000/zh

Watch out

MIT-licensed code, but 3 original examples are CC0 and 47 adapted stories plus translations are CC BY-SA 4.0 while user creations are not covered; needs Node.js 24 and npm, and BYOK keys pass through the deployer's server.

More like this

Jev workflow builder
115GitHub stars
A multiplayer demo workflow builder for Jev built with Liveblocks: wire Jev and LLM steps together, call the workflow through a REST API, and preview test runs with shared state and cursors.
Cookbooks & Demos#community#typescript#demo
Communityjev-workflow-builder
Jevmail
62GitHub stars
A local, read-only Gmail triage app that sorts mail into five trays with Jev: each message becomes one experimental_evaluate call answering tray, urgency, and human-written questions, and 1,000 emails sort in about a minute for around 3 cents.
Cookbooks & Demos#community#typescript#privacy
Communityjevmail
jev plays snake
21GitHub stars
A browser Snake game where code computes the legal moves, food distance, and reachable space and Jev picks one move per tick with a single Choice question; a late answer leaves the snake going straight.
Cookbooks & Demos#community#typescript#games
Communitytypesafe-snake
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Fast browser use with Stagehand

Kyle Jeong
Kyle Jeong
Browserbase
@kylejeong
·

we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 30 replies

LLM-as-a-judge, sped up

Yuchen Jin
Yuchen Jin
Databricks
@Yuchenj_UW
·

Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)

Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 94 replies

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter