FluidInference/FluidUse

Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

See decision-model runtime support for the current Core ML model matrix and handoff notes. Local computer use on Apple silicon. FluidUse reads a form in a running Mac app or browser through the Accessibility API, asks a small on-device model what belongs in each field, and types the answer into the real app. About 1 ms per decision on the Neural Engine, nothing leaves the machine. The first model is CUA-S1-FORMS, a 706K-parameter form specialist from Cua, converted to Core ML and served by FluidAudio. https://github.com/user-attachments/assets/a0b31285-05be-4bcf-a645-4283eb327c35 WebFormDriver does the same for an embedded WKWebView. DocumentEntities turns a PDF or text file of Label: value lines into the profile; an optional PredeterminedAnswer sheet covers question-style fields the model does not decide. laya (Convai Innovations, Apache-2.0) is an open Jev-style decision model: a 322M mmBERT encoder plus decision head that answers typed choice / score / noul questions about a text state…

FluidInference/FluidUse on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-09-27T12:44:55.632Z

Inside the original README — Document outline
  1. FluidUse
  2. Demo video
  3. Use
  4. laya typed decisions
  5. GLiNER 2.5 classification
  6. Kev decisions
  7. Demo
  8. Benchmarks
  9. Scope
  10. License

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API

Repository facts

Owner
FluidInference
Primary language
Swift
Stars
202
Forks
16
Open issues + pull requests
4
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-09-21T00:47:25.000Z
Last push
2026-09-27T04:38:06.000Z

Topics and intended use

Owner-supplied topics: accessibility-api, apple-silicon, computer-use, coreml, decision-model, macos, neural-engine, on-device-ai, swift

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-09-27T12:03:57.047Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

vorssaint/vorssaint-utils

Lakr233/vphone-cli

insidegui/WWDC

abue-ammar/tinycast

robbietilton/Compositor

Mak5er/AirCard