> ## Documentation Index
> Fetch the complete documentation index at: https://arizeai-433a7140-claude-llms-txt-2026-08-12.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Smolagents Tracing

> How to use the SmolagentsInstrumentor to trace smolagents by Hugging Face

export const projectName_0 = "my-llm-app"

smolagents is a minimalist AI agent framework developed by Hugging Face, designed to simplify the creation and deployment of powerful agents with just a few lines of code. It focuses on simplicity and efficiency, making it easy for developers to leverage large language models (LLMs) for various applications.

Phoenix provides auto-instrumentation, allowing you to track and visualize every step and call made by your agent.

<Card title="Google Colab" href="https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/smolagents_tracing_tutorial.ipynb" icon="https://ssl.gstatic.com/colaboratory-static/common/e2b7758e110827a5ed289fa36b2a079b/img/favicon.ico" horizontal>
  colab.research.google.com
</Card>

## Install

```bash theme={null}
pip install openinference-instrumentation-smolagents smolagents
```

## Setup

Add your `HF_TOKEN` as an environment variable:

```javascript theme={null}
os.environ["HF_TOKEN"] = "<your_hf_token_value>"
```

Connect your application to Phoenix with the `register` function:

<CodeBlock language="python">
  {`from phoenix.otel import register

    # configure the Phoenix tracer
    tracer_provider = register(
    project_name="${projectName_0}", # Default is 'default'
    auto_instrument=True # Auto-instrument your app based on installed OI dependencies
    )`}
</CodeBlock>

## Create & Run an Agent

Create your Hugging Face Model, and at every run, traces will be sent to Phoenix.

```python theme={null}
from smolagents import (
    CodeAgent,
    InferenceClientModel,
    ToolCallingAgent,
    VisitWebpageTool,
    WebSearchTool,
)

model = InferenceClientModel()

managed_agent = ToolCallingAgent(
    tools=[WebSearchTool(), VisitWebpageTool()],
    model=model,
    name="managed_agent",
    description="This is an agent that can do web search.",
)
managed_agent.run("Based on the latest news, what is happening in extraterrestrial life?")
```

## Observe

Now that you have tracing setup, all invocations and steps of your Agent will be streamed to your running Phoenix for observability and evaluation.

## Resources

* [OpenInference package](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-smolagents)

* [Working examples](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-smolagents/examples)

* [Smolagents Tracing Documentation](https://huggingface.co/docs/smolagents/en/tutorials/inspect_runs)