GitHub · Games and demos · Benchmarks and evaluation

virajbhartiya/laya-vs-jev

Watching both models make the same decision in the same second.

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

What it does

Runs Laya locally through MLX and Jev over TypeSafe's API on the same endless obstacle course, recording response times and crash replays so the two can be compared turn by turn.

The repository's own description: “Laya vs Jev: local MLX and hosted AI decisions playing T-Rex side by side, with live metrics and replay recording”

How it works

A physics planner generates the legal moves, each model picks one per step, and safety checks can override a stale or unsafe choice — which is exactly why the repository calls the scores assisted.

The repository, by the numbers

Stars

Licence

Apache-2.0

Stack

Python · MLX · TypeSafe API

Last push

2026-09-21

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 setup requirements, read 2026-09-24
the sentence about assisted scores measuring the combined system
the licence file

What we did not check. Any win rate or latency summary. The repository publishes the arena and the replays, not a results table, so there is no number here for us to quote even if we wanted one.

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

Heman10x-NGU/openJev-verdict-2.0

wdobry/laya-playground