Skip to content

Latest commit

 

History

History
135 lines (79 loc) · 5.05 KB

README.md

File metadata and controls

135 lines (79 loc) · 5.05 KB
Raw

○

Discord

The open-source language model computer.


OI-O1-BannerDemo-2

We want to help you build. Apply for 1-on-1 support.


⚠️ WARNING: This experimental project is under rapid development and lacks basic safeguards. Until a stable 1.0 release, ONLY run this repository on devices without sensitive information or access to paid services. ⚠️


The 01 Project is building an open-source ecosystem for AI devices.

Our flagship operating system can power conversational devices like the Rabbit R1, Humane Pin, or Star Trek computer.

We intend to become the GNU/Linux of this space by staying open, modular, and free.


Software

git clone https://github.com/OpenInterpreter/01 # Clone the repository
cd software/source # CD into the source directory

Not working? Read our setup guide.

brew install portaudio ffmpeg cmake # Install Mac OSX dependencies
poetry install # Install Python dependencies
export OPENAI_API_KEY=sk... # OR run `poetry run 01 --local` to run everything locally
poetry run 01 # Runs the 01 Light simulator (hold your spacebar, speak, release)

Hardware

  • The 01 Light is an ESP32-based voice interface. Build instructions are here. It works in tandem with the 01 Server running on your home computer.
  • Mac OSX and Ubuntu are supported by running poetry run 01. This uses your spacebar to simulate the 01 Light.
  • The 01 Heavy is a standalone device that runs everything locally.

We need your help supporting & building more hardware. The 01 should be able to run on any device with input (microphone, keyboard, etc.), output (speakers, screens, motors, etc.), and an internet connection (or sufficient compute to run everything locally). Contribution Guide →


How does it work?

The 01 exposes a speech-to-speech websocket at localhost:10001.

If you stream raw audio bytes to / in LMC format, you will recieve its response in the same format.

Inspired in part by Andrej Karpathy's LLM OS, we point a code-interpreting language model at your computer's kernel, forming a language model computer (LMC).


LMC

This architecture fuses classical computers— precise, powerful machines— with language models— imprecise, intelligent machines.

We believe the 01 inherits the best of both, unifying the power and connectivity of classical computers with the natural, human-like usability of language models.

Protocols

LMC Messages

To communicate with different componnents of this system, we introduced LMC Messages format, which extends OpenAI’s messages format to include the "computer" role.

Dynamic System Messages

Dynamic System Messages enable you to execute code inside the LLM's system message, moments before the "rendered" system message (which now includes the outputs of your code) is sent to the language model.

interpreter.system_message = r" The time is {{time.time()}}. " # Anything in double brackets will be executed as Python
interpreter.chat("What time is it?") # It will know, without making a tool/API call

Guides

Local Mode

poetry run 01 --local

If you want to run local speech-to-text using Whisper, you must install Rust. Follow the instructions given here.

Ubuntu Dependencies

sudo apt-get install portaudio19-dev ffmpeg cmake

Contributing

Please see our contributing guidelines for more details on how to get involved.


Roadmap

Visit our roadmap to see the future of the 01.


Background

Context ↗

The story of devices that came before the 01.

Inspiration ↗

Things we want to steal great ideas from.


○