OS Automation

TL;DR

CMDOP OS automation controls desktop environments programmatically. Move the mouse, click, type text, press key combinations, take screenshots, manage windows, and launch applications. Supports macOS, Windows, and Linux. Use natural language via cmdop chat or create YAML automation scripts. Requires accessibility permissions on macOS.

Automate desktop interactions programmatically.

What can CMDOP OS automation do?

Cmdop can control your desktop:

Mouse movements and clicks
Keyboard input
Screen capture
Window management
Application control

What are the requirements?

macOS

Accessibility permissions required
Grant in System Preferences > Security & Privacy > Accessibility

Windows

Run as Administrator for some operations

Linux

X11 or Wayland support
xdotool for X11 systems

What are the basic commands?

How do I control the mouse?


# Move mouse
cmdop os mouse move 100 200
 
# Click
cmdop os mouse click
 
# Right click
cmdop os mouse click --button right
 
# Double click
cmdop os mouse click --double

How do I send keyboard input?


# Type text
cmdop os keyboard type "Hello, World!"
 
# Press key
cmdop os keyboard press enter
 
# Key combination
cmdop os keyboard combo cmd+c

How do I capture the screen?


# Full screenshot
cmdop os screenshot
 
# Region
cmdop os screenshot --region 0,0,800,600
 
# Save to file
cmdop os screenshot --output ~/screenshot.png

How do I use AI-powered automation?

Use natural language with the AI:


# Start natural language OS automation via AI chat
cmdop chat


cmdop> open Chrome and go to github.com
cmdop> click the sign in button
cmdop> fill in my email and password

How do I create automation scripts?

Create automation scripts:


# automation.yaml
name: Daily Report
steps:
  - open: "Google Sheets"
  - wait: 2s
  - keyboard:
      combo: cmd+a
  - keyboard:
      combo: cmd+c
  - open: "Slack"
  - keyboard:
      type: "Here's the daily report:"
  - keyboard:
      combo: cmd+v

Run the script:


# Execute a YAML-defined desktop automation script
cmdop os run automation.yaml

How do I manage windows?


# List windows
cmdop os windows list
 
# Focus window
cmdop os windows focus "Terminal"
 
# Resize window
cmdop os windows resize "Terminal" 800 600
 
# Move window
cmdop os windows move "Terminal" 0 0

How do I control applications?


# Launch app
cmdop os app open "Visual Studio Code"
 
# Close app
cmdop os app close "Preview"
 
# List running apps
cmdop os app list

What are the common use cases?

Automated Testing - UI testing workflows
Data Entry - Automate repetitive form filling
Reporting - Generate and share reports
Integration - Connect apps that don’t have APIs