OpenJev

What it is

The open-source, local alternative to Jev: System-One decision models for agents. Typed questions in, calibrated probabilities out, in one forward pass. No text generation, no API key. Python package wev-ai (import wev) · models OpenJev-1.7B / 4B / 8B on the Hugging Face Hub

What the README says it does

• 🌐 Browser steps on unseen websites: 79% right, where open decision models trained on general data reach at
• 🧠 General decisions stay strong. OpenJev-4B scores 88.1 on Kev decision-v7 and 81.4 out of domain, and OpenJev beats
• 🎓 Better than its teacher, locally. As the System One of an open browser agent, OpenJev-4B completes 39–41 of 153
• ⚡ Fast. 10–40 ms for a general decision and 91–322 ms for a full browser page on one RTX 5090; 77 ms on a
• 📏 Calibrated. Probabilities you can threshold: raise the bar for DONE and early stops drop sharply.

From the project’s README.

Getting started

From the README:

pip install "openjev-ai[serve]"   # installs wev-ai, the package imported as wev

Where the decision sits

OpenJev calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev, laya.

How active it is

Created 2026-09-22, last pushed 2026-10-09, 70 stars and 4 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.