# X-PLUG/MobileAgent

Mobile-Agent: The Powerful GUI Agent Family

Repository: https://github.com/X-PLUG/MobileAgent
Canonical: https://ross.abutalabs.com/products/mobileagent
Language: Python
License: MIT
License Family: permissive
Topics: agent, mllm, mobile-agents, multimodal, multimodal-large-language-models, multimodal-agent, android, app, gui, mobile, automation, copilot
Last push: 2026-07-07T09:22:18+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 35, longevity 67
- inputs: {"age_days": 950, "days_push": 57, "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 9136, forks 909 (observed 2026-08-28T04:10:28.575271+00:00)

## What it is
Mobile-Agent is a family of multimodal GUI agents from Tongyi Lab that perceive and operate mobile and desktop user interfaces using vision-language models like GUI-Owl. It automates tasks on Android devices and computers by understanding screenshots and generating UI interactions.

## Use cases
- automate tasks on an android phone with an ai agent
- build a computer-use agent that clicks and types in a gui
- control mobile apps using screenshots and a multimodal llm
- run a gui agent on a cloud android phone
- benchmark or deploy a mobile gui automation agent

## When to choose
- you need an open-source GUI/mobile automation agent driven by vision-language models
- you want to automate Android app interactions without writing per-app scripts
- you are researching multimodal agents for UI understanding and grounding

## When to avoid
- you need simple deterministic UI test automation like Appium or Espresso
- you only need API-level mobile automation without visual perception
- you cannot run or access large multimodal models

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, computer-vision, machine-learning, workflow-automation, gui
- domain: artificial-intelligence, mobile-development, large-language-models
- platform: python, cross-platform
- tags: gui-agent, multimodal-llm, mobile-automation, computer-use, gui-owl, ui-grounding, ai-agents, automation, android

## Member repositories
- X-PLUG/MobileAgent (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.575271+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 2026-08-29T17:23:24.819507+00:00, confidence not recorded.
  - readme: https://github.com/X-PLUG/MobileAgent (fetched 2026-08-28T04:10:28.575271+00:00, sha 5b4a73a143b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.