Jev directory
CommunityJev Models & Reimplementations
JEV-Computer-Use
Hugging Face model card for JEV-Computer-Use, a System-One decision model for computer and browser use that reads out calibrated discrete action probabilities in a single forward pass instead of verbose text reasoning.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Single-token action readout (A, B, C...) targets sub-second decision latency
- Trained with Online Interactive GRPO against real headless Chromium via Playwright
- Combines cross-entropy, Brier calibration loss, and closed-form KL regularization
- Uses a Qwen vision-language judge as an automated semantic verifier
- Released under apache-2.0 with training and inference code on GitHub
Questions about this entry
Short answers drawn from the linked project or page.
It is a fast System-One decision model designed for high-speed computer use and browser navigation. Rather than emitting slow, verbose text reasoning before each mouse click, it uses a single-readout candidate slot formulation and outputs calibrated discrete action probabilities in one forward pass.
The model card describes a single-token action readout over candidate slots labeled A, B, C and so on, which the authors say enables sub-second decision latency instead of a reasoning chain preceding each click.
The Hugging Face model card lists the license as apache-2.0.
The card points to a GitHub repository at pidsana42-lgtm/JEV-Computer-Use, which holds the full training, data preprocessing, and Online GRPO environment code. The usage quickstart is to clone that repository, change into it, and run ./start.sh.
No. The model card states that the model is not deployed by any Inference Provider and invites users to ask for provider support.
Training uses Online Interactive GRPO with real headless Chromium through Playwright, plus a Qwen vision-language judge as an automated semantic verifier. The policy is trained with combined cross-entropy, Brier calibration loss, and analytical closed-form KL regularization.
The card tags the model with text generation, computer-use, gui-grounding, reinforcement-learning, grpo, qwen, playwright, and browser-agent.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Text-to-screenshot (Malay Vasa)
X: Standard One SH (StandardThinking)
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
X: Google's MediaPipe Decision Maker, tested in the browser
More Jev resources like this
Satirical Python script that answers a query with DO or DO_NOT plus a random confidence percentage, presented as a natural alternative to Jev. MIT-licensed, Python 3.8+, one dependency, no API keys or model weights.
Jev Models & Reimplementations#github#python#open-models
CommunityAhmad170412/Koin
A small, fast decision model — a system one model — for agentic workflows from Strands Labs: it picks between options or rates on a scale faster than an LLM and returns a calibrated confidence with every decision.
Jev Models & Reimplementations#community#github#python
Community
strands-labs/strands-deciderPython
strands-labs/strands-deciderPythonOpen Jev-style decision model built on LiquidAI's LFM2.5-350M backbone, a clone of kev. Serves the System One API contract so the TypeSafe SDK works against a local server, returning probabilities for typed questions from one forward pass.
Jev Models & Reimplementations#open-models#python#local
Communityfranckverrot/lev
Apache-2.0 Hugging Face repository for RSI-JEV-27b, a 27B multimodal decision model based on Qwen3.8-27B that answers supplied multiple-choice questions over images, returning a selected option and probabilities for all options in one forward pass.
Jev Models & Reimplementations#open-models#benchmark#calibration
Community
Russian-first open typed-decision model on Hugging Face. Given a context and a set of candidate options it returns a calibrated probability and picks one, covering yes/no, choice, and ordinal scale decisions. Built on mmBERT-base with 307M parameters under an MIT license.
Jev Models & Reimplementations#open-models#calibration#classification
Community
Open-weight vision-language judge that takes a task instruction plus 10 frames of a robot manipulation attempt and predicts success or failure with calibrated probabilities in a single forward pass. Released with inference code and a 20,628-prediction evaluation set.
Jev Models & ReimplementationsArticle#arxiv#open-models#evaluation
Community
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.