jev-phone
Drives a phone with Jev choosing each action while the phone-use runtime executes it on iOS and Android.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
jev-phone by rajmeet is described as a way to drive a phone with a model that never writes a word: TypeSafe's Jev picks each action and a phone-use runtime executes it on iOS and Android. It applies the familiar pattern of presenting a finite action list from the current screen and letting the decision model choose.
No README was available, so the action space, state encoding and maturity are unknown. The listing reports an MIT licence.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which action should the phone take next?(inferred) | — |
How it works
- Observe the phone screen through phone-use
- List possible actions
- Jev picks one
- phone-use executes it
Strengths
- No generated text or coordinates from the model
Caveats
- No README; details unknown
At a glance
- Type
- Project
- Runtime
- iOS and Android via phone-use
- License
- MIT
Use cases and integrations
How curated lists describe it
Drive a phone with a model that never writes a word. TypeSafe's Jev picks each action, phone-use runs it on iOS and Android.
logicrw/awesome-jev-projects
Frequently asked questions
What does Jev decide?
Each action the phone should take.
What executes the actions?
The phone-use runtime on iOS and Android.
Is it documented?
No README was available.
Related projects
Rust MCP server for desktop control via accessibility trees, with an optional decision model (Jev or compatible) for small choices.
MCP serverproductionRustmacOS menu-bar Swift app that turns on-device transcribed speech into Jev typed decisions and macOS actions, confirming hard-to-undo steps.
AppbetaSwiftRust CLI for desktop computer use via accessibility trees, with optional jev-desktop scripts letting Jev pick the control and action.
Agent skillbetaRustmacOS computer-use package: a background app driver for any agent, plus a loop where Jev picks each UI action for a bounded subtask.
ProjectbetaPythonLets coding agents run whole goals in your signed-in Chrome on macOS in background tabs, asking Jev or Claude Haiku only for real choices.
ProjectbetaComputer-use platform (Cua Spaces, Driver, Lume) with CUA-S1 small decision models and a preview jev-use example for bounded actions.
ProjectbetaPython