🐛 Debug Your Code Visually

import cammy

def process_data(df):
    cammy.snap("before transformation")
    df = df.transform(complex_operation)
    cammy.snap("after transformation")
    return df

🚨 Automatic Error Screenshots

import cammy

try:
    selenium_driver.click(button)
    api_response = fetch_data()
except Exception as e:
    cammy.snap()  # Auto-adds -stderr suffix
    raise

🔍 Monitor Long-Running Processes

import cammy

cammy.start()  # Start taking screenshots every second
train_model()  # Your long operation
cammy.stop()

# Multi-monitor monitoring
cammy.start(capture_all=True, interval=2.0)  # All monitors, 2s interval

🎬 Create GIF Summaries

import cammy

# Method 1: Use Context Manager
with cammy.session() as session:
    # ... your process ...

# Method 2: Start/Stop Manually
cammy.start()
# ... your process ...  
cammy.stop()
cammy.create_gif_from_latest_session()
# 📹 GIF created: ~/.cache/cammy/20250823_104523_summary.gif

Configuration

All configuration through function parameters - no config files needed!

cammy.start(
    output_dir="~/screenshots",  # Where to save
    interval=2.0,                # Seconds between captures
    quality=85,                  # JPEG quality (1-100)
    verbose=False,               # Silent mode
    monitor_id=0,                # Specific monitor (0-based)
    capture_all=False            # Capture all monitors
)

🖥️ Multi-Desktop & Monitor Features

import cammy

# Enumerate available monitors and windows
info = cammy.get_info()
print(f"Monitors: {info['Monitors']['Count']}")
print(f"Windows: {info['Windows']['VisibleCount']}")

# Capture specific monitor
cammy.snap(monitor_id=0)    # Primary monitor
cammy.snap(monitor_id=1)    # Secondary monitor

# Capture all monitors combined
cammy.snap(capture_all=True)

# Capture specific window by handle
windows = info['Windows']['Details']
if windows:
    handle = windows[0]['Handle']
    path = cammy.capture_window(handle)
    print(f"Captured window: {path}")

# Monitor specific screen continuously
cammy.start(monitor_id=1, interval=3.0)

File Structure

~/.cache/cammy/
├── 20250823_104523-message-stdout.jpg    # Normal capture
├── 20250823_104525-error-stderr.jpg      # Error capture  
└── 20250823_104530_0001_*.jpg            # Monitoring mode

Cache automatically managed (1GB default limit, oldest files removed)

Requirements

• Python 3.7+
• WSL environment (for Windows capture)
• PowerShell access to Windows host

Optional:

• Pillow - JPEG compression (recommended)
• mss - Cross-platform fallback

• AI Assistant Ready - Built-in MCP server for Claude Code and other AI assistants
• Direct Screenshot Control - AI can capture, monitor, and analyze screenshots programmatically
• Automated Workflows - Perfect for debugging, documentation, and monitoring tasks
• Real-time Interaction - AI assistants can respond to visual changes instantly

Setup - Just Add JSON!

// Add to your Claude Code settings
{
  "mcpServers": {
    "cammy": {
      "command": "python", 
      "args": ["-m", "cammy", "--mcp"]
    }
  }
}

Available MCP Tools

Core Capture:

• capture_screenshot - Take single screenshots with custom messages
• start_monitoring / stop_monitoring - Continuous monitoring at configurable intervals
• get_monitoring_status - Check current monitoring status

Analysis & Management:

• analyze_screenshot - AI-powered error detection and categorization
• list_recent_screenshots - Browse capture history by category (stdout/stderr)
• clear_cache - Manage screenshot cache size

Advanced Features:

• create_gif - Generate animated summaries from monitoring sessions
• list_sessions - List available sessions for GIF creation