# ipenywis/laya-ultrafast

> A local port of the jev-ultrafast browser agent that makes action decisions with the open-weight Laya model via MLX instead of a hosted API. Apple Silicon only, and it runs browser tasks without per-step cost.

- Magnitude: 4.7 out of 10 — Early signal
- Stars: 107 total · +51 stars today, ≈ 58 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-09-21 · Last push: 2026-09-22
- GitHub: https://github.com/ipenywis/laya-ultrafast · Page: https://gitnova.dev/en/r/ipenywis/laya-ultrafast

## Useful for

- Fill a website form from a goal without calling a hosted decision API
- Run a flight-search scenario on Google Flights or Skyscanner with final-page checks
- Set up a fully offline agent using a local text-model server such as Ollama

## Why it’s here

- 51 stars so far today, about 58 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 107 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #197.
- About 16 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 15
- Issues and pull requests: 1
- Watchers: 2
- Average over the last week: 57 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 4

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-22: 0, 56, 51

## Spotted in now

- Top new repositories this week: #197

## Similar by description

1. **browser-use/jev-ultrafast** — 8.3 · Peaking · AI agents · Python · +1,250 stars today, ≈ 1,459 by evening
   A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
   Full card: https://gitnova.dev/en/r/browser-use/jev-ultrafast.md
2. **browser-use/browser-use** — 3.7 · Steady · AI agents · Python · +116 stars today, ≈ 134 by evening
   Open-source Python library and CLI for AI agents that drive a browser: complete tasks on websites, fill forms and handle CAPTCHAs. Supports local runs, cloud browsers and a hosted API.
   Full card: https://gitnova.dev/en/r/browser-use/browser-use.md
3. **FluidInference/FluidUse** — 5.0 · Early signal · AI agents · Swift · +54 stars today, ≈ 62 by evening
   Local computer use on Apple silicon: reads forms in macOS apps via the Accessibility API, asks a small on-device model what belongs in each field, and types the answer into the real app.
   Full card: https://gitnova.dev/en/r/FluidInference/FluidUse.md
4. **mizorewww/laya-coreml** — 7.0 · Early signal · Language models · Python · +253 stars today, ≈ 292 by evening
   Local port of the Laya model to Apple Core ML and Neural Engine: returns typed decisions (choice, score, yes/no) without token generation, with speed and energy benchmarks.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-coreml.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-22 21:02 UTC, updated every 30 minutes.