Skip to content
JevDirectory.org
CommunityCookbooks & Demos11 starsVerified 2026-09-22

TypeSafe Experiments

Interactive browser experiments that expose Jev's judgments: a support-message Decision Lab and a driving simulation where structured sensor state becomes typed steer, brake, and overtake decisions.

Open github.comkavehmz/typesafe-playground
Category
Cookbooks & Demos
Published by
Community
Author
kavehmz
Added
2026-09-22
Tagscommunityjavascriptdemogamesplayground

Highlights

  • Three demos run side by side on ports 3001, 3002, and 3003: Decision Lab, Jev Driving Lab, and a Fable implementation.
  • In demo01 a support message becomes six independent judgments that ordinary code combines into an inspectable routing preview.
  • Driving demos give Jev structured simulated sensor observations, not camera images, and runs last 90, 120, or 180 seconds.
  • Needs Docker Compose or a compatible Podman setup and a TypeSafe API key; evaluations and driving runs make billable requests.
  • Routing is a preview: no real ticket is sent and no refund is issued, and camera views are rendered for the audience.

Quickstart

bash
cp -n .env.example .env
# edit .env and set TYPESAFE_API_KEY to YOUR_API_KEY
docker compose -f demo01/compose.yaml up -d --build
docker compose -f demo02/compose.yaml up -d --build

Watch out

No license file, so reuse terms are unclear; requires Docker with Compose or a compatible Podman setup and a TypeSafe API key, and live evaluations or auto-restarting driving runs make billable requests.

More like this

jev-leftpad
78GitHub stars
A joke npm package that left-pads a string by asking Jev to choose among space_0 through space_10 in one Choice, spending a model call where padStart() would do.
Cookbooks & Demos#community#javascript#demo
Communityjev-leftpad
EmbodiedJev
181GitHub stars
A MuJoCo and Franka Panda workbench where Jev chooses the next manipulation step for pick-and-place, stacking, and obstacle-carry tasks, with rule baselines and side-by-side model comparison.
Cookbooks & Demos#community#python#robotics
Communityembodied-jev
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
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Full Jev video tutorial

The case against Jev-scored compaction

Theo - t3.gg
Theo - t3.gg
@theo
·

This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the Show more

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 182 replies

Classifying rows in DuckDB

A playable 16-judgment demo

AI multiple choice, not essay writing

Screening agent actions with Jev

😎Nick 常胜
😎Nick 常胜
@isNickMa
·

Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor. Checking each action first worked well caught most attacks with almost no false blocks, and much faster than Gemini.

Image
Image
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 1 reply