> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orkestration.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Install Orkestra and run your first workflow in minutes.

Welcome to Orkestra! This guide will help you get up and running in minutes.

**For more information, visit [Orkestration.com](https://orkestration.com).**
**For detailed documentation, visit [docs.orkestration.com](https://docs.orkestration.com).**

## Installation

```bash theme={null}
pip install orkestra-sdk
```

## Run a Simple Workflow

Here's how to create and run a simple two-step workflow:

```python theme={null}
from orkestra import Orkestra

# 1. Initialize your client
# You'll need an OpenAI API key for this example.
# Set it as an environment variable or pass it directly.
orkestra_client = Orkestra()

# 2. Create specialized agents
researcher = orkestra_client.Agent(
    name="Researcher",
    description="Gathers detailed information on a topic.",
    model_provider="openai",
    model_name="gpt-4o",
    api_secret="YOUR_OPENAI_API_KEY",
)

summarizer = orkestra_client.Agent(
    name="Summarizer",
    description="Condenses complex information into a concise summary.",
    model_provider="openai",
    model_name="gpt-3.5-turbo",
    api_secret="YOUR_OPENAI_API_KEY",
)

# 3. Create a workflow and chain the agents
workflow = (
    orkestra_client.Workflow()
    .add(researcher)
    .add(summarizer)
)

# 4. Run the workflow
prompt = "What are the key differences between nuclear fission and fusion?"
result = workflow.run(prompt)

print(result)
```