---
title: "Custom Hardware"
description: "Control 01 from your own device"
---

You can create custom hardware that integrates with the O1 server software running on your computer.

To use 01 with your custom hardware, run the server:

```bash
poetry run 01 --server
```

You may need to set additional parameters via [flags](/software/flags) depending on your setup.

To transmit audio commands to 01, send LMC audio chunks to the websocket defined by your server.

## LMC Messages

To support the incoming `L`anguage `M`odel `C`omputer architecture, we extend OpenAI's messages format to include additional information, and a new role called `computer`:

```python
# The user sends a message.
{"role": "user", "type": "message", "content": "What's 2380*3875?"}

# The assistant runs some code.
{"role": "assistant", "type": "code", "format": "python", "content": "2380*3875"}

# The computer responds with the result of the code.
{"role": "computer", "type": "console", "format": "output", "content": "9222500"}

# The assistant sends a message.
{"role": "assistant", "type": "message", "content": "The result of multiplying 2380 by 3875 is 9222500."}
```

## Anatomy

Each message in the LMC architecture has the following parameters (`format` is only present for some types):

```
{
  "role": "<role>",       # Who is sending the message.
  "type": "<type>",       # What kind of message is being sent.
  "format": "<format>"    # Some types need to be further specified, so they optionally use this parameter.
  "content": "<content>", # What the message says.
}
```

| Parameter | Description                           |
| --------- | ------------------------------------- |
| `role`    | The sender of the message.            |
| `type`    | The kind of message being sent.       |
| `content` | The actual content of the message.    |
| `format`  | The format of the content (optional). |

## Roles

| Role        | Description                                             |
| ----------- | ------------------------------------------------------- |
| `user`      | The individual interacting with the system.             |
| `assistant` | The language model.                                     |
| `computer`  | The system that executes the language model's commands. |

## Possible Message Types / Formats

Any role can produce any of the following formats, but we've included a `Common Roles` column to give you a sense of the message type's usage.

| Type    | Format      | Content Description                                                                                                                 | Common Roles            |
| ------- | ----------- | ----------------------------------------------------------------------------------------------------------------------------------- | ----------------------- |
| message | None        | A text-only message.                                                                                                                | `user`, `assistant`     |
| console | active_line | The active line of code (from the most recent code block) that's executing.                                                         | `computer`              |
| console | output      | Text output resulting from `print()` statements in Python, `console.log()` statements in Javascript, etc. **This includes errors.** | `computer`              |
| image   | base64      | A `base64` image in PNG format (default)                                                                                            | `user`, `computer`      |
| image   | base64.png  | A `base64` image in PNG format                                                                                                      | `user`, `computer`      |
| image   | base64.jpeg | A `base64` image in JPEG format                                                                                                     | `user`, `computer`      |
| image   | path        | A path to an image.                                                                                                                 | `user`, `computer`      |
| code    | html        | HTML code that should be executed.                                                                                                  | `assistant`, `computer` |
| code    | javascript  | JavaScript code that should be executed.                                                                                            | `assistant`, `computer` |
| code    | python      | Python code that should be executed.                                                                                                | `assistant`             |
| code    | r           | R code that should be executed.                                                                                                     | `assistant`             |
| code    | applescript | AppleScript code that should be executed.                                                                                           | `assistant`             |
| code    | shell       | Shell code that should be executed.                                                                                                 | `assistant`             |
| audio   | wav         | audio in wav format for websocket.                                                                                                  | `user`                  |