> For the complete documentation index, see [llms.txt](https://nx.docs.scailable.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-manager-plugin/quick-start.md).

# Plugin Quick Start

Get the AI Manager running on your first device in five steps.

This page guides you through the complete setup from zero to your first AI detection. Each step links to the detailed documentation; come back here if you lose your place.

## Key Terms

The following terms appear throughout these docs:

* **AI Manager:** The full package: Plugin, Runtime, and Cloud together.
* **AI Manager Plugin:** The plugin that runs on an edge device inside Nx Meta. It lets you configure the AI pipeline for each device.
* **AI Runtime:** The library component that runs AI models on AI accelerators. The Plugin controls the Runtime; the Runtime manages the accelerator and the downloaded model files.
* **AI Manager Cloud:** The web platform for managing devices and models and building your personal model catalogue.
* **AI/ML model:** Any definition that transforms input (a stream of images) into output such as bounding boxes, a license plate string, or an OK/NG classification.
* **Edge device:** Any device (camera, gateway, IPC, etc.) running the AI Manager.

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-14c20ac923c36d71520a69a620ba8b45a13f46f5%2Fplugin-components-diagram.png?alt=media" alt="AI Manager Plugin component diagram showing AI Runtime managing the AI
     Accelerator and AI/ML Model"><figcaption><p>The AI Manager Plugin: the Runtime manages the AI Accelerator and the AI/ML Model running inside the Nx platform.</p></figcaption></figure>

## Step 1: Check System Requirements

Before installing anything, confirm your hardware and OS are supported.

{% content-ref url="/pages/qDZwbJbgQKfjDu2FwxZ3" %}
[System requirements](/ai-manager-v6.1.4/ai-manager-plugin/quick-start/system-requirements.md)
{% endcontent-ref %}

## Step 2: Install Nx Meta

Install the Nx Meta server and client on your machine.

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-a5dcaee54bd93b7b96ca524d6344af155ce84116%2Fcloud-login.png?alt=media" alt="The AI Manager Cloud admin interface login screen"><figcaption><p>The AI Manager Cloud admin interface - log in with your Nx account to continue</p></figcaption></figure>

{% content-ref url="/pages/4ue4YahlwQB2AhkuOAHz" %}
[Install Server and Client](/ai-manager-v6.1.4/ai-manager-plugin/quick-start/install-server-and-client.md)
{% endcontent-ref %}

## Step 3: Enable the AI Manager Plugin

Open the desktop client, right-click a camera, go to **Camera Settings → Integrations**, and enable the AI Manager toggle.

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-a0b26aedb553d5dece0f65beac51fef29bf76c5c%2Fclient-ai-manager-disabled.png?alt=media" alt="Camera Settings dialog with the Integrations tab selected, showing AI
     Manager listed in the plugin list"><figcaption><p>Camera Settings Integrations tab: the AI Manager plugin appears here once installed.</p></figcaption></figure>

{% content-ref url="/pages/iFRdkGmk2C4WNa5SV9PF" %}
[Starting the plugin](/ai-manager-v6.1.4/ai-manager-plugin/quick-start/starting-the-plugin.md)
{% endcontent-ref %}

## Step 4: Configure a Model Pipeline

Open the AI Manager panel for the camera select a pipeline, enable the camera if it is not enabled already and click "Apply" to save the settings.

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-631fcc609c639cf891b1ac0e7dc3d1db438fffcf%2Fclient-ai-manager-people-vehicles-pipeline.png?alt=media" alt="AI Manager pipeline panel showing People and Vehicles Detection model
     configured with sensitivity and postprocessor controls"><figcaption><p>The pipeline panel with a model assigned: adjust sensitivity and postprocessor settings here.</p></figcaption></figure>

{% content-ref url="/pages/6EEE07YOwLbczVzy2LX3" %}
[Configure the plugin](/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin.md)
{% endcontent-ref %}

## Step 5: Confirm It Works

Switch to the **Objects** tab in the desktop client. Bounding boxes or other model output appear on the camera feed within a few seconds.

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-f46321e42fd6d33ce19d59ff440bc4aa47f4f793%2Fclient-live-view-object-thumbnails-panel.png?alt=media" alt="Live View with four people detected and labeled, and the Objects panel
     listing each detection with a thumbnail and timestamp"><figcaption><p>The Objects tab shows AI detections from the running model pipeline.</p></figcaption></figure>

{% content-ref url="/pages/6EEE07YOwLbczVzy2LX3#confirming-it-works" %}
[Configure the plugin](/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin.md#confirming-it-works)
{% endcontent-ref %}

{% hint style="success" %}
If you see detections, you are done. To manage models at scale across many devices, continue to the [AI Manager Cloud](/ai-manager-v6.1.4/ai-manager-cloud-ui/introduction.md) section.
{% endhint %}

{% hint style="info" %}
If nothing appears, go to [Troubleshooting](/ai-manager-v6.1.4/support-and-troubleshooting/troubleshooting.md).
{% endhint %}