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

# SDK

The OpenGPU Python SDK allows developers to interact with the network programmatically.

**Docs**: [opengpu-network.github.io/sdk-ogpu-py](https://opengpu-network.github.io/sdk-ogpu-py/)

## What It Does

* Publish sources and tasks via code
* Monitor task status and retrieve results
* Manage accounts and payments
* Integrate OpenGPU into your applications

## Current Status

The SDK is in early stages of development. Core functionality is available, with more features being added.

## Basic Usage

```python
from ogpu.client import publish_task, TaskInfo, TaskInput, get_task_responses

# Publish a task
task_info = TaskInfo(
    source_address="0x...",
    task_input=TaskInput(
        function_name="process",
        input_data={"prompt": "Hello, world!"}
    ),
    expiry_time=3600,
    payment=0.01
)

task_address = publish_task(task_info)

# Get responses
responses = get_task_responses(task_address)
```

## Key Capabilities

| Feature             | Status    |
| ------------------- | --------- |
| Task submission     | Available |
| Source publishing   | Available |
| Result retrieval    | Available |
| Account management  | Available |
| Streaming responses | Planned   |

## Who It's For

* Developers building AI applications on the OpenGPU Network
* Teams automating GPU workflows
* Anyone needing programmatic access

> See [SDK Documentation](https://opengpu-network.github.io/sdk-ogpu-py/) for API reference.