# Nx AI Manager plugin version 6.1.1

<figure><img src="https://4052997117-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkP02geOjtLSPAt4JiZUv%2Fuploads%2FNcOMnCnPLrMxCafdc2aT%2Fnx-ai-manager-logo-simple-white.svg?alt=media&#x26;token=73ca2da8-53d8-4153-96c1-59afee08dc7e" alt=""><figcaption></figcaption></figure>

The Nx AI Manager plugin is a tool that enables you to create and manage large-scale Edge AI solutions using the [Network Optix toolkit](https://www.networkoptix.com/developers/nx-toolkit). With this plugin, you can turn any compatible edge device, like a router, gateway, or IPC, into a "smart" device that can run advanced Artificial Intelligence (AI) and Machine Learning (ML) models on input data. Using AI and ML models, you can analyze a video stream and gain valuable insights, such as counting the number of cars passing by in the video stream.

The documentation here offers detailed instructions on setting up and configuring your edge AI solutions on Linux-based Nx Meta-supported edge hardware.

## The Nx AI Manager plugin Architecture.

The Nx AI Manager plugin is the starting point for creating AI solutions within the Nx Meta framework. It can run within Nx Meta Server on any supported edge device (such as a smart camera, gateway, and PC) and allows you to configure the solution you want to create by selecting an AI model and configuring the device settings.&#x20;

The Nx AI Manager plugin currently mainly focuses on video input (a stream of images from a camera).

You can use the Nx Cloud Platform to remotely configure your solution and manage it at scale: i.e., if you have hundreds of devices, you can manage them in one go.&#x20;

The core "magic" that goes into creating edge AI solutions is the **AI model**; the model effectively transforms the input (images) to the desired output (a count of the number of people in front of the camera, an "OK" / "NG" output for product inspection, the license plate of a car in front of the camera, or whether or not a person in front of the camera is wearing a helmet). We have some of off-the-shelf models in our model library, allowing users to configure new solutions. However, if you are a data scientist, you can create models and upload them to our platform for your custom needs.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://nx.docs.scailable.net/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.