> ## 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.

# Basic Agent

> Run an agent on a HuggingFace model in sync, streaming, and async modes.

## Code

```python huggingface_basic.py theme={null}
import asyncio

from agno.agent import Agent
from agno.models.huggingface import HuggingFace

agent = Agent(
    model=HuggingFace(
        id="mistralai/Mistral-7B-Instruct-v0.2", max_tokens=4096, temperature=0
    ),
)

if __name__ == "__main__":
    # --- Sync ---
    agent.print_response(
        "What is meaning of life and then recommend 5 best books to read about it"
    )

    # --- Sync + Streaming ---
    agent.print_response(
        "What is meaning of life and then recommend 5 best books to read about it",
        stream=True,
    )

    # --- Async ---
    asyncio.run(
        agent.aprint_response(
            "What is meaning of life and then recommend 5 best books to read about it"
        )
    )

    # --- Async + Streaming ---
    asyncio.run(
        agent.aprint_response(
            "What is meaning of life and then recommend 5 best books to read about it",
            stream=True,
        )
    )
```

## Usage

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

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

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

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

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