atl-browser

Community

Vision-free automation for iOS Safari and apps.

AuthorJordanCoin
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Automates mobile browser and native-app tasks on iOS simulators via a two-server architecture and a vision-free workflow, enabling deterministic interactions without relying on visual AI.

Core Features & Use Cases

  • Dual-server automation (Browser on port 9222 and Native on port 9223) for seamless Web and app workflows.
  • Vision-free workflow with element marking, coordinate taps, and a clear escalation ladder (coordinates → vision → JS) for robust automation across iOS Safari and native apps.
  • Hybrid browser-native automation patterns and OpenClaw integration to empower AI agents with end-to-end task execution.

Quick Start

Install ATL to your macOS device, start the ATL servers on the simulator, and connect via the OpenClaw skill to begin issuing commands.

Dependency Matrix

Required Modules

curljqbase64

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: atl-browser
Download link: https://github.com/JordanCoin/Atl/archive/main.zip#atl-browser

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.