# FluidInference/FluidUse

> 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.

- Magnitude: 5.0 out of 10 — Early signal
- Stars: 111 total · +45 stars today, ≈ 60 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Swift · License: Apache-2.0 · Created: 2026-09-21 · Last push: 2026-09-22
- GitHub: https://github.com/FluidInference/FluidUse · Homepage: https://huggingface.co/FluidInference · Page: https://gitnova.dev/en/r/FluidInference/FluidUse

## Useful for

- Fill a form in Safari or WKWebView from a Label: value profile without sending data off-device
- Run the laya model for choice/score/noul questions about text with calibrated probabilities
- Measure CUA-S1-FORMS and laya decision latency on the Neural Engine via built-in benchmarks

## Why it’s here

- 45 stars so far today, about 60 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 111 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #187.
- About 11 forks a day — people are taking the code.
- Recent forks include notable developers: @dorucioclea (311 followers).

## 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: 7
- Issues and pull requests: 5
- Watchers: 0
- Average over the last week: 63 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 3
- Latest release: v0.2.0 (2026-09-21)

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

2026-09-20 … 2026-09-22: 2, 65, 45

## Spotted in now

- Top new repositories this week: #187

## Similar by description

1. **mizorewww/laya-coreml** — 6.9 · Early signal · Language models · Python · +206 stars today, ≈ 290 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
2. **NandhaKishorM/laya** — 9.2 · Breakout · AI agents · Python · +3,318 stars today, ≈ 4,567 by evening
   Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.md
3. **kraayenjon/awesome-jev** — 3.3 · Early signal · Learning & lists · +10 stars today, ≈ 14 by evening
   A curated list of resources for Jev, TypeSafe AI's System One model that returns typed decisions (Choice, Score, Noul) with calibrated probabilities instead of generated text. Aimed at developers integrating Jev into code.
   Full card: https://gitnova.dev/en/r/kraayenjon/awesome-jev.md
4. **mizorewww/laya-mlx** — 8.6 · Breakout · Language models · Python · +845 stars today, ≈ 1,205 by evening
   Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-mlx.md
5. **daseinlabs/open-jev** — 2.5 · Early signal · Language models · Python · +5 stars today, ≈ 8 by evening
   Local server and CLI for scoring pre-written options with an LLM: computes each option's log-probability in a single prefix-shared forward pass without decoding, running Gemma 3 4B on Apple Silicon via MLX.
   Full card: https://gitnova.dev/en/r/daseinlabs/open-jev.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 17:57 UTC, updated every 30 minutes.