# load_extensions

> **Function** in `deepagents_code`

📖 [View in docs](https://reference.langchain.com/python/deepagents-code/extensions/runtime/load_extensions)

Load every authorized extension while isolating failures.

## Signature

```python
load_extensions(
    *,
    cwd: Path | None = None,
    mode: ExtensionMode = ExtensionMode.INTERACTIVE,
    project_root: Path | None = None,
    project_trust_granted: bool = False,
    cli_paths: tuple[Path, ...] = (),
) -> ExtensionLoadResult
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `cwd` | `Path \| None` | No | Working directory exposed to factories. (default: `None`) |
| `mode` | `ExtensionMode` | No | Runtime mode. (default: `ExtensionMode.INTERACTIVE`) |
| `project_root` | `Path \| None` | No | Project whose local extensions may be considered. (default: `None`) |
| `project_trust_granted` | `bool` | No | Explicit one-run project grant. (default: `False`) |
| `cli_paths` | `tuple[Path, ...]` | No | Explicit one-run extension files or directories. (default: `()`) |

## Returns

`ExtensionLoadResult`

Successful registrations and error messages.

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/e4c1ffe9ee63d7854147de490ca27495ef157a7b/libs/code/deepagents_code/extensions/runtime.py#L79)