> For the complete documentation index, see [llms.txt](https://sacha-levy.gitbook.io/hulse/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sacha-levy.gitbook.io/hulse/getting-started.md).

# Getting Started

**Welcome to Hulse beta!**

**Leverage your team's unused computing power to seamlessly host open-source Natural Language Processing models from 🤗 Hugging Face's model hub.**

Start reading below to learn how to use the Hulse API, and set up the Hulse desktop app. The desktop app beta is currently only available on macOS, but you may use the Hulse CLI to run a host from your terminal.

If you have questions or want to talk about anything related to Hulse, you are welcome to join the community on [Discord](https://discord.gg/uPf74RXSC2)!

Hulse is currently in beta, please report bugs or any feedback you may find (on [Github](https://github.com/hulsedev/hulse-py), or [Discord](https://discord.gg/uPf74RXSC2))!

### Requirements

* Python 3.7 for the Hulse Python Client
* macOS Monterey for the Hulse desktop app

## Quickstart Tutorial

### Steps

Hulse pools the unused computing power within your teams' PCs. To do so, your team members must join a common Hulse cluster, as well as download the Hulse macOS desktop app (or use the Hulse CLI to run a host) on their computers.

1. Login to the [Hulse dashboard](https://hulse-api.herokuapp.com/login) & create or join a cluster.
2. [Download the Hulse desktop app](https://hulse-desktop.s3.amazonaws.com/universal2/Hulse.dmg), and start hosting from your computer.
3. (optional) Setup the [Hulse Python client](https://github.com/hulsedev/hulse-py) & query open-source models.&#x20;

### For the team (steps 1 & 2)

{% embed url="<https://youtu.be/ZlxNS5q6wBc>" %}

### For developers (step 3)

{% embed url="<https://youtu.be/eaRG3pxkJiE>" %}

For a detailed walkthrough of Python Client methods, see [this section](/hulse/developers/hulse-py.md). For more information on the presented use case, see [the example section](/hulse/developers/tweet-sentiment-example.md).
