> ## Documentation Index
> Fetch the complete documentation index at: https://docs.askui.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> What is AgentOS, why it exists, and the key concepts you need to know.

AgentOS is the runtime layer that gives AI agents direct control over a machine's operating system — keyboard, mouse, screen, and system-level functions. It sits between your agent code and the OS, handling the low-level interactions so your agents can focus on tasks.

**Designed for everyone, not just developers.** AgentOS is built so that non-technical users can install it and get it running without writing code or configuring system internals. The UI installer guides you through setup, the SDK auto-detects the service, and sensible defaults mean you don't need to touch configuration files to get started.

**Platform independent.** AgentOS runs on Windows, macOS, and Linux. In [Companion Mode](/06-agent-os/understanding/control-modes#companion-mode), it can also control Android devices, iOS Simulators (experimental), and any machine reachable through hardware interfaces — regardless of what OS the target runs.

## How It Works

AgentOS operates in two **control modes**:

* **[Host Mode](/06-agent-os/understanding/control-modes#host-mode)** — AgentOS runs directly on the target machine as software. It controls the desktop via OS-level APIs with full access to screenshots, input, windows, and processes.
* **[Companion Mode](/06-agent-os/understanding/control-modes#companion-mode)** — AgentOS runs on an external device (e.g. Raspberry Pi) and controls the target machine through hardware interfaces (USB, Bluetooth, HDMI capture). No software installation on the target required.

Both modes expose the same **capabilities** to your agents — the building blocks for screen reading, input simulation, window management, and more.

## Why AgentOS?

Building a Computer Use Agent (CUA) proof-of-concept is straightforward — a few scripts with PyAutoGUI or xdotool and you have a demo running in minutes. But getting it to **production** is a different story. The gap between "works on my machine" and "runs reliably at scale" is where most teams get stuck. CI/CD integration is where it gets especially painful — VMs start at the logon screen, automation requires an interactive user session, and OS security restrictions block input injection from non-interactive processes. Solving this means dealing with session management, login automation, and privilege escalation before your agent can even begin its work.

See our detailed comparisons for more:

<CardGroup cols={2}>
  <Card title="vs Automation Libraries" icon="code" href="/06-agent-os/understanding/comparison/vs-automation-libs">
    PyAutoGUI, RobotJS, xdotool, and why they fall short in production.
  </Card>

  <Card title="vs Remote Control Software" icon="display" href="/06-agent-os/understanding/comparison/vs-remote-control">
    RDP, TeamViewer, VNC, RustDesk — built for humans, not agents.
  </Card>
</CardGroup>

## What's Next?

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/06-agent-os/installation/standalone">
    Get AgentOS running in under 5 minutes.
  </Card>

  <Card title="Control Modes" icon="desktop" href="/06-agent-os/understanding/control-modes">
    Host Mode vs Companion Mode — how AgentOS connects to targets.
  </Card>

  <Card title="Deployment" icon="sitemap" href="/06-agent-os/how-to-guides/deployment-scenarios">
    Find the right setup for your target.
  </Card>
</CardGroup>