> ## 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.

# Connect to AgentOS and inspect its configuration

> Both the synchronous ``get_config`` method and its asynchronous ``aget_config`` twin.

```python connect.py theme={null}
"""Connect to AgentOS and inspect its configuration.

This example shows both the synchronous ``get_config`` method and its
asynchronous ``aget_config`` twin.

Prerequisites: start ``_server.py`` in another terminal.
Run: .venvs/demo/bin/python cookbook/05_agent_os/03_python_client/01_connect.py
Try: compare the component IDs returned by the sync and async calls.
"""

import asyncio

from agno.client import AgentOSClient
from agno.os.schema import ConfigResponse

BASE_URL = "http://localhost:7778"


# ---------------------------------------------------------------------------
# Create the Client
# ---------------------------------------------------------------------------


def print_config(label: str, config: ConfigResponse) -> None:
    """Print the components advertised by AgentOS."""
    print(f"{label}: {config.name or config.os_id}")
    print(f"Agents: {[agent.id for agent in config.agents]}")
    print(f"Teams: {[team.id for team in config.teams]}")
    print(f"Workflows: {[workflow.id for workflow in config.workflows]}")


def connect_sync() -> None:
    """Use the synchronous discovery method."""
    client = AgentOSClient(base_url=BASE_URL)
    print_config("Synchronous connection", client.get_config())


async def connect_async() -> None:
    """Use the asynchronous discovery method."""
    client = AgentOSClient(base_url=BASE_URL)
    print_config("Asynchronous connection", await client.aget_config())


# ---------------------------------------------------------------------------
# Run the Example
# ---------------------------------------------------------------------------

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

## Run the Example

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

**1. Install dependencies**

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

**2. Export your API keys**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Clone Agno**

Clone the pinned Agno source and run the remaining commands from its root:

```bash theme={null}
git clone https://github.com/agno-agi/agno.git
cd agno
git checkout v3.0.4
```

**4. Start the AgentOS server**

Open another terminal in the parent directory where `.venv` and the cloned `agno` directory are siblings, then start the shared server on port 7778:

```bash Mac/Linux theme={null}
source .venv/bin/activate
export OPENAI_API_KEY="your_openai_api_key_here"
cd agno
python cookbook/05_agent_os/03_python_client/_server.py
```

```powershell Windows theme={null}
.venv\Scripts\activate
$Env:OPENAI_API_KEY="your_openai_api_key_here"
Set-Location agno
python cookbook/05_agent_os/03_python_client/_server.py
```

**5. Run the example**

Run the example from the repository root:

```bash theme={null}
python cookbook/05_agent_os/03_python_client/01_connect.py
```

Full source: [cookbook/05\_agent\_os/03\_python\_client/01\_connect.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/05_agent_os/03_python_client/01_connect.py)


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