> ## 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 Basic Agent

> Stream a WatsonX agent's response with stream=True.

## Code

```python basic.py theme={null}
from typing import Iterator  # noqa

from agno.agent import Agent, RunOutputEvent  # noqa
from agno.models.ibm import WatsonX

agent = Agent(
    model=WatsonX(id="mistralai/mistral-small-3-1-24b-instruct-2503"), markdown=True
)

# Get the response in a variable
# run_response: Iterator[RunOutputEvent] = agent.run("Share a 2 sentence horror story", stream=True)
# for chunk in run_response:
#     print(chunk.content)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story", stream=True)
```

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export IBM_WATSONX_API_KEY=xxx
    export IBM_WATSONX_PROJECT_ID=xxx
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U ibm-watsonx-ai agno
    ```
  </Step>

  <Step title="Run Agent">
    Save the code above as `basic.py`, then run:

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

Setting `stream=True` when calling `print_response()` or `run()` enables token-by-token streaming with IBM WatsonX.