GitHub · Serving and API · Runtime ports

alvarobartt/sys1

A Rust service that wants token-based batching without writing the HTTP layer.

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

What it does

Serves open decision models behind the System One API spec, starting with Laya's ModernBERT weights and its custom decision heads, so a client written for that protocol can talk to a local model.

The repository's own description: “System One compatible API for open decision models, e.g. Laya, written in Rust.”

How it works

axum handles the HTTP surface, candle runs the model on CPU, CUDA or Metal, and requests are batched by token count rather than arrival order so that a long prompt does not stall a short one behind it.

The repository, by the numbers

Stars

Licence

Apache-2.0

Stack

Rust · candle · axum

Last push

2026-09-23

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 its feature list, read 2026-09-24
the stated per-query figure and the GPU it was measured on
the licence file

What we did not check. Whether the wire format matches TypeSafe's clients field for field. Settling that takes both ends running, and we did not stand the server up.

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

mizorewww/laya-mlx

mizorewww/laya-coreml

receptron/laya