Today is launch day. Read our <ahref="https://changes.openinterpreter.com/log/the-new-computer-update">founding statement →</a>
</p>
<br> -->
```shell
pip install 01OS
```
> Not working? Read our [setup guide](https://docs.openinterpreter.com/getting-started/setup).
```shell
01 # Run this to start the 01.
```
<br>
### [View task list ↗](https://github.com/KillianLucas/01/blob/main/TASKS.md)
**The 01 project** is an open-source ecosystem for artificially intelligent devices.
By combining code-interpreting language models with speech recognition and voice synthesis, the 01’s flagship operating system (the 01OS) can power conversational, computer-operating AI devices similar to the Rabbit R1 or the Humane Pin.
We intend to become the “Linux” of this space— open, modular, and free for personal or commercial use.
[View all providers ↗](https://docs.litellm.ai/docs/providers/), or [join the 01 team by adding a service provider. ↗]()
- **Requirements:** Ensure that Node.js is installed ([Node.js Download](https://nodejs.org/en/download)), then run:
```
npm install -g localtunnel
```
- **To Expose:**
```bash
01 --server --expose-with-localtunnel
```
### Run the 01 locally
- **ngrok** ([Website](https://ngrok.com/))
- **Requirements:** Install ngrok ([Getting Started with ngrok](https://ngrok.com/docs/getting-started/)), and set up an ngrok account. Get your auth key from [ngrok dashboard](https://dashboard.ngrok.com/get-started/your-authtoken), then set it in your local configuration by running:
```
ngrok config add-authtoken your_auth_token_here
```
- **To Expose:**
```bash
01 --server --expose-with-ngrok
```
Some service providers don't require an internet connection.
**Run a specific client:**
The following command will attempt to download and use the best providers for your hardware:
```bash
01 --client macos # Options: macos, rpi
```shell
01 --local
```
**Run locally:**
The current default uses OpenAI's services.
## How Does it Work?
The `--local` flag will install and run the [whisper.cpp](https://github.com/ggerganov/whisper.cpp) STT and [Piper](https://github.com/rhasspy/piper) TTS models.
The 01 equips a language model (wrapped in a voice interface) with an `exec()` function, which allows it to write and run code to control computers.
```bash
01 --local # Local client and server
01 --local --server --expose-with-bore # Expose the local server with a public tunnel
```
We only stream speech to/from the end user's device.
**Teach Mode (experimental)**
# Contributing
Running `01 --teach` runs 01 in teach mode, where you can add your own skills for Open Interpreter to use, through an easy-to-follow GUI.
<br>
Please see our [contributing guidelines](docs/CONTRIBUTING.md) for more details on how to get involved.
## Setup for development:
### Setup for development
```bash
# Clone the repo, cd into the 01OS directory
# Clone the repo
git clone https://github.com/KillianLucas/01.git
# Go to the 01OS directory
cd 01OS
# Install dependencies, run the commands above
# Install python dependencies
poetry install
# Run it
poetry run 01
```
**Configuration:**
<br>
# Roadmap
Copy the `01OS/.env.example` file to `01OS/.env` then configure the environment variables within the file.
Visit [our roadmap](https://github.com/KillianLucas/open-interpreter/blob/main/docs/ROADMAP.md) to see the future of the 01.
killian
10 months ago