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

# AutoGen AgentChat Tracing

> Auto-instrument your AgentChat application for seamless observability

[AutoGen AgentChat](https://microsoft.github.io/autogen/stable//user-guide/agentchat-user-guide/index.html) is the framework within Microsoft's AutoGen that enables robust multi-agent application.

<Tabs>
  <Tab title="Phoenix Cloud">
    **Sign up for Phoenix:**

    1. Sign up for an Arize Phoenix account at [https://app.phoenix.arize.com/login](https://app.phoenix.arize.com/login)

    2. Click `Create Space`, then follow the prompts to create and launch your space.

    **Install packages:**

    ```bash theme={null}
    pip install arize-phoenix-otel
    ```

    **Set your Phoenix endpoint and API Key:**

    From your new Phoenix Space

    1. Create your API key from the Settings page

    2. Copy your `Hostname` from the Settings page

    3. In your code, set your endpoint and API key:

    ```python theme={null}
    import os

    os.environ["PHOENIX_API_KEY"] = "ADD YOUR PHOENIX API KEY"
    os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "ADD YOUR PHOENIX HOSTNAME"

    # If you created your Phoenix Cloud instance before June 24th, 2025,
    # you also need to set the API key as a header:
    # os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={os.getenv('PHOENIX_API_KEY')}"
    ```

    <Info>
      Having trouble finding your endpoint? Check out [Finding your Phoenix Endpoint](/docs/phoenix/resources/frequently-asked-questions/what-is-my-phoenix-endpoint)
    </Info>
  </Tab>

  <Tab title="Command Line">
    **Launch your local Phoenix instance:**

    ```bash theme={null}
    pip install arize-phoenix
    phoenix serve
    ```

    For details on customizing a local terminal deployment, see [Terminal Setup](/docs/phoenix/environments#terminal).

    **Install packages:**

    ```bash theme={null}
    pip install arize-phoenix-otel
    ```

    **Set your Phoenix endpoint:**

    ```javascript theme={null}
    import os

    os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "http://localhost:6006"
    ```

    See [Terminal](/docs/phoenix/environments#terminal) for more details.
  </Tab>

  <Tab title="Docker">
    **Pull latest Phoenix image from** [**Docker Hub**](https://hub.docker.com/r/arizephoenix/phoenix)**:**

    ```bash theme={null}
    docker pull arizephoenix/phoenix:latest
    ```

    **Run your containerized instance:**

    ```bash theme={null}
    docker run -p 6006:6006 arizephoenix/phoenix:latest
    ```

    This will expose the Phoenix on `localhost:6006`

    **Install packages:**

    ```bash theme={null}
    pip install arize-phoenix-otel
    ```

    **Set your Phoenix endpoint:**

    ```javascript theme={null}
    import os

    os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "http://localhost:6006"
    ```

    For more info on using Phoenix with Docker, see [Docker](/docs/phoenix/self-hosting/deployment-options/docker).
  </Tab>

  <Tab title="Notebook">
    **Install packages:**

    ```bash theme={null}
    pip install arize-phoenix
    ```

    **Launch Phoenix:**

    ```javascript theme={null}
    import phoenix as px
    px.launch_app()
    ```

    <Info>
      By default, notebook instances do not have persistent storage, so your traces will disappear after the notebook is closed. See [self-hosting](/docs/phoenix/self-hosting) or use one of the other deployment options to retain traces.
    </Info>
  </Tab>
</Tabs>

## Install

```bash theme={null}
pip install openinference-instrumentation-autogen-agentchat autogen-agentchat autogen_ext
```

## Setup

Connect to your Phoenix instance using the register function.

```python theme={null}
from phoenix.otel import register

# configure the Phoenix tracer
tracer_provider = register(
  project_name="agentchat-agent", # Default is 'default'
  auto_instrument=True # Auto-instrument your app based on installed OI dependencies
)
```

## Run AutoGen AgentChat

We’re going to run an `AgentChat` example using a multi-agent team. To get started, install the required packages to use your LLMs with `AgentChat`. In this example, we’ll use OpenAI as the LLM provider.

```sh theme={null}
pip install autogen_ext openai
```

```python expandable theme={null}
import asyncio
import os
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_ext.models.openai._openai_client import OpenAIChatCompletionClient

os.environ["OPENAI_API_KEY"] = "your-api-key"

async def main():
    model_client = OpenAIChatCompletionClient(
        model="gpt-4",
    )

    # Create two agents: a primary and a critic
    primary_agent = AssistantAgent(
        "primary",
        model_client=model_client,
        system_message="You are a helpful AI assistant.",
    )

    critic_agent = AssistantAgent(
        "critic",
        model_client=model_client,
        system_message="""
        Provide constructive feedback.
        Respond with 'APPROVE' when your feedbacks are addressed.
        """,
    )

    # Termination condition: stop when the critic says "APPROVE"
    text_termination = TextMentionTermination("APPROVE")

    # Create a team with both agents
    team = RoundRobinGroupChat(
        [primary_agent, critic_agent],
        termination_condition=text_termination
    )

    # Run the team on a task
    result = await team.run(task="Write a short poem about the fall season.")
    await model_client.close()
    print(result)

if __name__ == "__main__":
    asyncio.run(main())
```

## Observe

Phoenix provides visibility into your AgentChat operations by automatically tracing all interactions.

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/agentchat-phoenix.png" />
</Frame>

## Resources

* [AutoGen AgentChat documentation](https://microsoft.github.io/autogen/stable//user-guide/agentchat-user-guide/index.html)

* [AutoGen AgentChat OpenInference Package](https://pypi.org/project/openinference-instrumentation-autogen-agentchat/)