Built with Open reimplementations
arbiter
Serve typed-decision (System 1) models — Laya or your own — on NVIDIA GPUs or Apple Silicon, with a Jev-compatible API and coding-agent integrations
35 ★ on GitHub
What it is
Serve typed-decision models — Laya or your own — on your GPU or your Mac, with a Jev-compatible API.
Getting started
From the README:
git clone https://github.com/0xBakeer/arbiter.git
cd arbiter
./run.sh setup # .venv, torch, the deps, and the three checkpoints (2.3 GB)
./run.sh serve # http://localhost:8010Where the decision sits
arbiter 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-typed-decisions, jev, laya-multilingual, laya-typed-decisions, laya, laya.
How active it is
Created 2026-09-20, last pushed 2026-09-24, 35 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.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.