GitHub · Serving and API

0xBakeer/arbiter

Serving your own trained head behind the API a Jev client already speaks.

The repository's GitHub card, read on 2026-09-24

What it does

Stands up typed-decision models as a service, including Laya and heads you trained on your own data, and answers the Jev API shape so an existing client can be pointed at it unchanged.

The repository's own description: “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”

How it works

The model runs in a local process, a request carries the state and the questions together, and the response returns an answer and a probability distribution per question from a single forward pass.

The repository, by the numbers

Stars

Licence

MIT

Stack

Python · GPU / Apple Silicon

Last push

2026-09-20

Read from the GitHub API on 2026-09-24. Stars and the last push move daily — quote them with the date, the way we do.

What we checked

the README and the build write-up it links, read 2026-09-24
the compatibility claim and the API section that backs it
the licence file

What we did not check. Behaviour under concurrent load. The repository documents a working single-machine setup, not a throughput measurement, and we did not load it.

Open the repository ↗All builds

The rest of the topic

Jev, the reference →

Start here

Laya, the reference What it is, what we measured running it, and what it is not.
Laya and Jev, compared The two models on the same questions, including the ones Laya loses.

Columns

Built with Laya 18 you are here Ports, servers, agents and games, with what we checked.
What X is saying 22
What people filmed 9
What Hacker News made of it 6
Docs, weights and reading 15

The topic

Every record, by kind of work The same rows cut a second way, across every column.
What self-hosting costs Hardware, memory, and the failure modes of running it yourself.
What the licence allows Apache-2.0 weights, three checkpoints, and the limits that come with them.

By kind of work

Runtime ports 23 Getting the weights onto someone else's hardware: MLX on a Mac, Core ML on the Neural Engine, ggml in C++, candle in Rust, ONNX in Node.
Serving and API 8 Standing the model up as something else can call, usually behind Jev's own wire format.
Agents and tools 6 Typed decisions inside an agent loop: routing, evals, guardrails, memory, and the plumbing around them.
Browser and computer use 2 Deciding the next click, key or field on a real screen.
Games and demos 9 The model playing something you can watch. Most of this model's traffic arrived through one of these.
Benchmarks and evaluation 19 Numbers somebody actually ran — including the ones that say Laya lost.

What it does

How it works

The repository, by the numbers

What we checked

More like this

receptron/laya

lkarlslund/laya.cpp

1Panel-dev/laya-server