How Bytebot’s desktop agent works under the hood
/mcp
@bytebot/shared
User Input
Task Creation
AI Planning
Action Execution
Desktop Automation
Result Processing
User Feedback
Services: All on one machine Scale: 1 instance each Use Case: Personal automation, development Resources: 4GB RAM, 2 CPU cores
Services: All services on dedicated hardware Scale: Single instance (1 agent, 1 desktop) Use Case: Business automation Resources: 8GB+ RAM, 4+ CPU cores
Services: Kubernetes orchestration Scale: Single instance with high availability Use Case: Organization-wide automation Resources: Dedicated nodes
FROM bytebot/desktop:latest RUN apt-get update && apt-get install -y \ your-custom-tools