lev

What it is

lev is an open System One decision model and the harness that measures it. Give it a state (text, a ticket, an email, or JSON) and a set of typed questions (yes/no, choice, score), and it answers all of them in one forward pass, reading each answer from logits it already computed. It returns calibrated probabilities…

The homepage listed on the repository, huggingface.co, puts it like this: Zero-Shot Classification model. Download, explore files and run it on Hugging Face.

Getting started

From the README:

pip install "lev[serve] @ git+https://github.com/Abhinavexists/lev#subdirectory=packages/lev"

Where the decision sits

lev 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-mlx.

How active it is

Created 2026-09-20, last pushed 2026-10-15, 58 stars and 3 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.