GitHub · Browser and computer use

ipenywis/laya-ultrafast

Browser automation on an Apple laptop with no per-step cost.

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

What it does

Drives a browser where every action is chosen by a local Laya model instead of a hosted API call, keeping Browser Use's agent loop, DOM snapshot and safety checks intact.

The repository's own description: “Same as jev-ultrafast but using Laya”

How it works

The page state is reduced to text, the model picks among the actions the harness offers, and one text-model call per step covers what the typed decisions cannot express.

The repository, by the numbers

Stars

149

Licence

MIT

Stack

Python · Apple Silicon · MLX

Last push

2026-09-22

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, including the paragraph crediting the original project, read 2026-09-24
the Apple-silicon-only requirement and the median latency claim
the licence file

What we did not check. The 33 ms median and the agent's success rate on real sites. No row in this column reports a success rate, and this one is no exception.

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

ThinkFlowLab/system1-agents