# Overview

## What is DeGirumJS?

> **DeGirumJS** is a powerful JavaScript library designed for building and integrating AI applications directly in your browser. This SDK allows you to perform AI inference using models hosted on a local DeGirum AI Server or in the DeGirum Cloud, directly from your web browser.

***

## Quickstart

Use DeGirumJS with a single line of code. No installation is required: include the following script tag in your HTML page:

{% code overflow="wrap" %}

```html
<script src="https://assets.degirum.com/degirumjs/0.1.5/degirum-js.min.obf.js"></script>
```

{% endcode %}

## Key Features

* **Pure Vanilla JavaScript**: Written entirely in JavaScript with no external dependencies.
* **Simple Integration**: Seamlessly connect to local AI servers or the cloud for inference.
* **Real-Time Inference**: Perform AI tasks using local models or by using DeGirum's vast cloud library of models in real-time.

## Ready to dive in?

Start by exploring the [**Getting Started Guide**](/degirumjs/get-started.md) or browse the [**API Reference**](https://docs.degirum.com/degirumjs/0.1.5/api/index.html) for more detailed usage and options.

Or, browse the advanced topics:

* [Model Parameters](/degirumjs/guides/model-parameters.md)
* [Connection Modes](/degirumjs/guides/connection-modes.md)
* [Real-Time Batch Inference](/degirumjs/guides/batch-inference.md)
* [Performance & Timing Statistics](/degirumjs/guides/timing.md)
* [Customizing Pre-processing and Visual Overlays](/degirumjs/guides/pre-post-processing.md)
* [Working with Input and Output Data](/degirumjs/guides/input-output-data.md)
* [Device Management for Inference](/degirumjs/guides/device-management.md)
* [Result Object Structure + Examples](/degirumjs/guides/result-object-structure.md)
* [WebCodecs Example](/degirumjs/guides/web-codecs-example.md)
* [Release Notes](/degirumjs/all-release-notes.md)

Start building your browser-based AI projects with DeGirumJS.


---

# 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://docs.degirum.com/degirumjs/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.