> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/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.

## Run the Example

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

**1. Install dependencies**

```bash theme={null}
uv pip install -U "agno[anthropic]"
```

**2. Set your API key**

```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"
```

**3. Save and run**

Save the example as `basic_stream.py`, then run:

```bash theme={null}
python basic_stream.py
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.