Playground
CommunityJev Demos & Experiments
JEV-9B — typed decisions
A Hugging Face Space by ikaraoha titled JEV-9B — typed decisions, duplicated from autotrust/jev-9b-decision-demo. It presents an interactive browser demo of a JEV-9B model producing typed decisions, and is served from Hugging Face Zero hardware.
- Format
- Playground
- Reading time
- 2 min
- Published by
- Community
- Added
- Oct 2026
Highlights
- Hugging Face Space published by the user ikaraoha.
- Duplicated from the autotrust/jev-9b-decision-demo Space.
- Titled JEV-9B — typed decisions.
- Runs on Zero hardware within Hugging Face Spaces.
- Space page exposes App, Files, and Community tabs.
Questions about this entry
Short answers drawn from the linked project or page.
It is a Hugging Face Space published by ikaraoha under the title JEV-9B — typed decisions. The Space is a browser demo of a JEV-9B model that returns typed decisions, and it is duplicated from the autotrust/jev-9b-decision-demo Space rather than built from scratch.
The listing names ikaraoha as the publisher. The page states that the Space was duplicated from autotrust/jev-9b-decision-demo, so the original owner is autotrust and ikaraoha holds the copy you are viewing.
The Space page indicates it is running on Zero, the free Hugging Face Spaces tier. That means the demo shares free-tier compute rather than running on dedicated or upgraded hardware, so response speed and availability depend on that shared capacity.
The listing shows a standard public Hugging Face Space with App, Files, and Community tabs, and it displays a Get PRO prompt alongside them. Nothing in the listing indicates that an API key is required to open the demo page itself.
The listing does not describe it as an official TypeSafe AI Space. It names ikaraoha as the publisher and autotrust/jev-9b-decision-demo as the duplication source, so treat it as a third-party Space rather than a first-party release.
The available listing only shows the Space title, publisher, duplication source, Zero hardware, and the App, Files, and Community tabs, plus a note that metadata is being fetched from the Hugging Face Docker repository. It does not describe weights, datasets, or evaluation numbers.
Avoid depending on it for anything time-sensitive or production-facing. It runs on Zero free-tier hardware, the page shows it still refreshing repository metadata, and the listing gives no stability, throughput, or uptime guarantees.
More Jev resources like this
A browser playground that turns prompts into abstract art through Jev's structured decisions, updating only the relevant fields of an 80+ characteristic renderer spec as you type, while comparing Jev with a single-call LLM, sandboxed custom JavaScript, and prompt-to-image generation.
Jev Demos & ExperimentsPlayground#playground#demo#javascript
Browser demo that sends one text to TypeSafe Jev and lights up 200 yes/no judgments as a live heatmap in roughly 150-300 ms, with seven 200-question sets, a threshold slider, and zero npm dependencies.
Jev Demos & ExperimentsPlayground#demo#browser#javascript
Communitycharles-forsyth/jev-decision-wall
A Hugging Face Space by Tonic that pairs MiniCPM-OCR with a Jev checker and serves the app from a Docker repository. Visitors can open the hosted page to try the OCR-plus-check flow without setting anything up locally.
Jev Demos & ExperimentsPlayground#demo#madewithjev#playground
Community
Browser and terminal demo that ranks emoji against a free-text query by sending one Jev score question per emoji, then filtering by a tunable score floor and limit. Includes a bench harness over saved queries.
Jev Demos & Experiments#madewithjev#demo#typescript
Communitynischal94/emoji-sift
Minecraft survival bot built on Mineflayer that asks Jev four typed questions every 600ms — threat level, action, whether to eat, flee direction — plus a tactical goal-selection loop, with simulated emotions and persistent memory feeding each request.
Jev Demos & Experiments#demo#games#madewithjev
Communityakash-kamat/jev-craft
Spanish-language prototype that uses Jev to classify event sign-ups and decide program, action, and message before sending, with a guardrail that approves, flags, or blocks outgoing text. Includes synthetic datasets, evaluation scripts, and a local engine that runs without a key.
Jev Demos & Experiments#madewithjev#demo#python
Communityblockstars-labs/30x-JEV
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.