Skip to main content

πŸš€ Quick Setup

1. Install and Activate

2. Run Your First Agent

πŸ“‹ Common Commands

Agent-Specific Commands

Auto-Close Agent

Social Media Agent

LinkedIn Agent

Slack Support Agent

Shopify Agent

General Purpose Commands

πŸ”§ Configuration Examples

Setting Display Resolution

Edit main.py:

API key Configuration

Replace in main.py:

Custom Agent Selection Logic

Add to get_active_agents() function:

πŸ“Š Monitoring Commands

View Logs in Real-Time

Check Screenshots

Start every new automation in dry-run and watch a full pass before letting it act. Computer-use failures are rarely a crash β€” the agent clicks a plausible wrong thing and continues β€” so the useful signal is watching one run end to end, not waiting for an error.

πŸ› οΈ Troubleshooting Commands

Check Dependencies

Test Display

Verify API Connectivity

πŸ’‘ Usage Examples

Example 1: Close Support Tickets

Example 2: Social Media Monitoring

Example 3: LinkedIn Outreach

Example 4: Slack Customer Support

Example 5: Shopify Management

πŸ”‘ Key Environment Variables

πŸ“ˆ Performance Tips

  1. Run Multiple Agents: Use ”&” to run agents in background
  2. Limit Token Usage: Modify in code
  3. Reduce Screenshot Frequency: Modify in code

πŸ›‘οΈ Security Quick Checks

πŸ“ Notes

  • Always use Ctrl+C for graceful shutdown
  • Screenshots are saved in screenshots/{AGENT_TYPE}/
  • Logs show [AGENT_TYPE] prefix for easy filtering
  • Billing only occurs for completed tasks
  • Virtual display must be running (DISPLAY=:1)

For detailed documentation, see USERGUIDE.md

Next steps

Architecture overview

How the pieces you just started fit together.

Computer Use Agent

The full platform reference.

Computer-use MCP

Driving these agents from an MCP client.

Engines MCP

Choosing an execution engine.
Last modified on August 29, 2026