# OminousIndustries/PhoneDriver

Android Phone Control With Qwen3-VL

Repository: https://github.com/OminousIndustries/PhoneDriver
Canonical: https://ross.abutalabs.com/products/phonedriver
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-10-24T18:34:21+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 48, release rhythm 35, longevity 23
- inputs: {"age_days": 323, "days_push": 313, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1614, forks 262 (observed 2026-08-28T04:05:11.134322+00:00)

## What it is
PhoneDriver is a Python-based mobile automation agent that uses Qwen3-VL vision-language models to visually understand and control Android devices via ADB commands. It includes a built-in Gradio web UI for issuing natural language tasks with live screenshots and execution logs.

## Use cases
- automate android phone tasks with natural language
- control my phone with a vision language model
- ai agent that taps and swipes on android via adb
- test android apps by describing tasks in plain english
- run qwen3-vl locally to drive a phone screen
- automate repetitive phone actions without writing scripts

## When to choose
- you want local, self-hosted vision-based Android automation with a GPU
- you need natural language control of an Android device over ADB
- you want to experiment with Qwen3-VL agents on real phone screens

## When to avoid
- you need iOS or non-Android device automation
- you have no local GPU (24GB VRAM recommended)
- you need production-grade, scalable mobile test infrastructure rather than a hobbyist agent

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, machine-learning, computer-vision, workflow-automation, gui, developer-tools
- domain: artificial-intelligence, android-tools, mobile-development, computer-vision
- platform: python, windows
- tags: qwen3-vl, vision-language-model, adb, android-automation, gradio, phone-control, self-hosted-llm, ai-agents, automation, android, linux, macos, gpu

## Member repositories
- OminousIndustries/PhoneDriver (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:11.134322+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:50:19.868363+00:00, confidence not recorded.
  - readme: https://github.com/OminousIndustries/PhoneDriver (fetched 2026-08-28T04:05:11.134322+00:00, sha 0caa5aedfab5)
- Data as of 2026-08-30T08:39:29.467469+00:00.