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

# Streaming Agent

> Stream a Claude response through an Agno agent.

```python basic_stream.py theme={null}
from agno.agent import Agent
from agno.models.anthropic import Claude

agent = Agent(
    model=Claude(id="claude-sonnet-4-5-20250929"),
    markdown=True,
)

if __name__ == "__main__":
    agent.print_response("Write a two-sentence horror story.", stream=True)
```

`stream=True` emits content as it arrives. When iterating over `agent.run()` directly, set `stream_events=True` to include lifecycle and tool events in addition to content events.

<Note>
  `agent.run(..., stream=True)` returns an iterator. API or network errors that
  occur after the stream starts are raised while that iterator is consumed.
</Note>

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[anthropic]"
    ```
  </Step>

  <Step title="Set your API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export ANTHROPIC_API_KEY="your_anthropic_api_key"
      ```

      ```powershell Windows theme={null}
      $Env:ANTHROPIC_API_KEY="your_anthropic_api_key"
      ```
    </CodeGroup>
  </Step>

  <Step title="Save and run">
    Save the example as `basic_stream.py`, then run:

    ```bash theme={null}
    python basic_stream.py
    ```
  </Step>
</Steps>