# AsyncSubAgent

> **Class** in `deepagents`

📖 [View in docs](https://reference.langchain.com/python/deepagents/middleware/async_subagents/AsyncSubAgent)

Specification for an async subagent running on a remote Agent Protocol server.

Async subagents connect to any Agent Protocol-compliant server via the
LangGraph SDK. They run as background tasks that the main agent can
monitor and update.

Compatible with LangGraph Platform (managed) and self-hosted servers.
Authentication for LangGraph Platform is handled automatically by the SDK
via environment variables (`LANGGRAPH_API_KEY`, `LANGSMITH_API_KEY`, or
`LANGCHAIN_API_KEY`). For self-hosted servers, pass custom auth via
`headers`.

## Signature

```python
AsyncSubAgent()
```

## Extends

- `TypedDict`

## Constructors

```python
__init__(
    name: str,
    description: str,
    graph_id: str,
    url: NotRequired[str],
    headers: NotRequired[dict[str, str]],
)
```

| Name | Type |
|------|------|
| `name` | `str` |
| `description` | `str` |
| `graph_id` | `str` |
| `url` | `NotRequired[str]` |
| `headers` | `NotRequired[dict[str, str]]` |


## Properties

- `name`
- `description`
- `graph_id`
- `url`
- `headers`

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/64ecf141be0479f859f4efe25d139166b45ee18c/libs/deepagents/deepagents/middleware/async_subagents.py#L34)