> 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/readme.md).

# AI Manager plugin version 6.1.2

<figure><img src="/files/44dX6m4Stc1f7fkuExxu" alt=""><figcaption></figcaption></figure>

The AI Manager is a plugin for the [Network Optix toolkit](https://www.networkoptix.com/developers/nx-toolkit) that lets you run AI and ML models on edge devices (routers, gateways, IPCs, and smart cameras) and analyze live video streams. You can count vehicles, detect objects, read license plates, or run any other vision model against a camera feed.

This documentation covers setup and configuration of edge AI solutions on Linux-based hardware supported by Nx Meta.

## Architecture

The plugin runs inside Nx Meta Server on any supported edge device. It takes a camera's video stream as input, runs an AI model against each frame, and returns results: bounding boxes, classification scores, event triggers, and so on.

The **AI Cloud** lets you manage and deploy models to any number of devices from a single browser interface. Assign or swap a model on one device or on thousands at once.

The **AI model** is what determines what the plugin detects or measures. Off-the-shelf models are available in the model library. Data scientists can upload custom models to the platform for organization-specific use cases.