Mwebesanorman/Open-AutoGemini

View on GitHub by @Mwebesanorman

🤖 Automate tasks on Android, iOS, and HarmonyOS with Open-AutoGemini, an easy-to-deploy framework powered by Gemini's advanced AI capabilities.

What's novel

🤖 Automate tasks on Android, iOS, and HarmonyOS with Open-AutoGemini, an easy-to-deploy framework powered by Gemini's advanced AI capabilities.

Code Analysis

5 files read · 2 rounds

An AI-powered mobile phone automation framework that uses LLMs (Gemini/OpenAI) to control Android and iOS devices via ADB/HDC/XCUITest protocols to perform tasks like app launching, tapping, typing, and swiping.

Strengths

Well-architected modular design with clear separation by platform (iOS/Android/HarmonyOS), comprehensive action handling system, robust device connection management, and good error messaging. The framework supports multiple model APIs and provides both CLI and Web UI interfaces.

Weaknesses

No test files present despite having pytest in dev dependencies, README significantly misrepresents the project as a generic data analysis tool rather than an automation agent, minimal dependency list suggests incomplete setup, and lacks comprehensive documentation for advanced usage.

Score Breakdown

Innovation

5 (25%)

Craft

69 (35%)

Traction

11 (15%)

Scope

66 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+2

Concept Novelty+0

Craft

Ci+0

Tests+8

Polish+1

Releases+0

Has License+5

Code Quality+21

Readme Quality+15

Recent Activity+7

Structure Quality+5

Commit Consistency+2

Has Dependency Mgmt+5

Traction

Forks+0

Stars+6

Hn Points+0

Watchers+0

Early Traction+0

Devto Reactions+0

Community Contribs+5

Scope

Commits+8

Languages+3

Subsystems+10

Bloat Penalty+0

Completeness+7

Contributors+8

Authored Files+12

Readme Code Match+3

Architecture Depth+5

Implementation Depth+8

Evidence

Commits

100

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

Apache-2.0