Complete documentation and development guides for the AgentBay SDK
- Installation Guide - SDK installation and environment setup
- Basic Concepts - Understand cloud environments and sessions
- First Session - 5-minute quick start with hands-on examples
- Feature Guides Overview - Complete feature guides introduction
- Common Features Guide - Features available across all environments
- Session Management - Cloud environment lifecycle management
- Command Execution - Execute shell commands and scripts
- File Operations - File upload, download, and management
- Data Persistence - Cross-session data storage
- Custom Images - Create tailored environments with specific configurations
- Session Link Access - Session connectivity and URL generation
- Agent Modules - AI-powered task automation
- OSS Integration - Object Storage Service integration
- SDK Configuration - Configuration options and settings
- Use Cases Overview - Common use case scenarios and implementations
- Session Info Use Cases - Session information and connectivity patterns
- Session Link Use Cases - Connect external tools to cloud sessions
Complete browser automation for web scraping, testing, and form filling.
- Core Features - Basic browser operations
- Advanced Features - Advanced browser capabilities
- Code Examples - Practical code samples
- Browser Extensions - Extension management
- Browser Replay - Session replay functionality
- Integrations - Third-party integrations
Key Capabilities:
- Browser Context - Context management
- Browser Proxies - Network proxy configuration
- CAPTCHA Handling - Automated CAPTCHA solving
- Extension Support - Browser extension management
- Browser Fingerprint - Simulate browser fingerprint
- Call for User - User interaction requests
- Page Agent - AI-driven page operations
Windows desktop automation for application control and window management.
- Computer Application Management - Application control and management
- Computer UI Automation - Desktop UI interaction and automation
- Window Management - Window operations and focus management
- Browser Capabilities by Image Type - Understanding browser support across different images
Key Capabilities:
- Application Management (start, stop, list applications)
- Window Operations (maximize, minimize, resize, close)
- Focus Management
- Desktop Automation Workflows
Mobile UI automation for app testing and gesture-based interactions.
- Mobile Application Management - Mobile app control and management
- Mobile UI Automation - Mobile UI interaction and automation
- ADB Connection - ADB connection and debugging capabilities
- Mobile Session Configuration - Advanced mobile session configuration options
Key Capabilities:
- UI Element Detection
- Click Operations and Text Input
- Key Events and Swipe Gestures
- Screenshot Capture
- Mobile Application Management
- ADB Connection and Debugging
Development environment for code execution and scripting.
- Code Execution - Python and JavaScript code execution
Key Capabilities:
- Python and JavaScript Code Execution
- Shell Command Execution
- File System Operations
- Development Tools Integration
- Package Management (pip, npm, etc.)
An AI-powered Agent to complete tasks descibed in natural language
- Agent Guide - Agent task execution guide
Key Capabilities:
- Office Automation: Word/Excel/PowerPoint automation
- File Operations: Create/Delete/Move/Copy files and folders
- Infomation Gathering: Gather information from the Internet
- Text Edition: Using notepad to edit text file
- Python SDK - Python version documentation
- TypeScript SDK - TypeScript version documentation
- Golang SDK - Golang version documentation
Choose the appropriate learning path based on your experience level:
Start from the basics and build your knowledge step by step:
- Basic Concepts - Understand core concepts
- Installation Guide - Environment setup
- First Session - Hands-on practice
- Feature Guides - Explore specific features as needed
Already familiar with browser automation, computer use, or mobile testing? Start here:
Quick Start (5 minutes):
- Installation - Set up your preferred SDK (Python/TypeScript/Golang)
- Choose your environment based on your use case:
- 🌐 Browser Automation - Web scraping, testing, form filling with stealth capabilities
- 🖥️ Computer/Windows Automation - Desktop UI automation and window management
- 📱 Mobile Automation - Android UI testing and gesture automation
- 💻 CodeSpace - Cloud-based code execution environments
What makes AgentBay different:
- Session Link - Direct URL access to services running in cloud sessions
- Agent Modules - AI-powered automation capabilities
Need more details? See Advanced Features or language-specific API docs: Python | TypeScript | Golang
- GitHub Issues - Report bugs or request features
💡 Tip: We recommend starting with the Quick Start Tutorial, then exploring specific feature guides as needed.