# Client App

The Client App is a web application for publishing sources and tasks to the OpenGPU Network. Currently in beta (v0.2).

**URL**: [client.opengpu.network](https://client.opengpu.network)

## What It Does

* Publish and manage Sources
* Publish Tasks (for testing or occasional manual jobs)
* Manage Vault balances and stakes

For programmatic task publishing (e.g. inference jobs), use the [SDK](/opengpu-network/ecosystem/sdk.md) or interact with the protocol directly via RPC.

## Source Creation Flow

The app guides you through a 5-step source creation process:

1. **Select Model Type**: Choose what kind of model you're deploying
2. **Upload Compose Files**: Provide Docker Compose YAML files for different hardware environments (CPU, NVIDIA GPU), or use the Hugging Face Ready option for direct integration
3. **Define Constraints**: Set requirements for providers who will run your model
4. **Source Information**: Enter name, description, and logo
5. **Review and Confirm**: Review and submit (you sign the transaction)

## Key Features

### Source Publishing

* Direct Hugging Face integration
* Custom YAML upload for CPU and GPU environments
* Hardware constraint configuration
* Payment and timing settings

### Task Publishing

* Submit tasks to your Sources
* Set payment amounts and deadlines
* Monitor execution status
* Retrieve results

### Vault Management

* View and manage $OGPU balance
* Manage stakes

## Who It's For

* AI researchers deploying models
* Developers testing on distributed GPUs
* Anyone publishing Sources or occasional Tasks

> See [For Clients: Publishing Sources](/opengpu-network/for-clients/publishing-sources.md) for detailed instructions.


---

# 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://opengpu-network.gitbook.io/opengpu-network/ecosystem/client-app.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.