Skip to main content
SoloTech is how ML engineers make real robots intelligent. We provide the hardware, libraries, and remote control capabilities so developers can collect data, train AI models and deploy applications to real robots in minutes instead of months.

Highlights

  • ๐Ÿ“น Rapid Data Acquisition: Use a leader arm for controlling robots and recording training datasets quickly.
  • ๐Ÿง  Model Training Acceleration: Train state-of-the-art action models (e.g., SmolVLA, ACT, PI0, TDMPC) efficiently.
  • ๐Ÿ”— Hardware Compatibility: Fully compatible with the SO-101 robotic platform.
  • ๐Ÿ’ก Accessible Development: Simple, intuitive, developer-friendly API.
  • ๐Ÿค Ecosystem Integration: Fully compatible with the LeRobot and HuggingFace ML platforms.
  • ๐Ÿ’ป Cross-Platform Support: Operates across macOS, Linux, and Windows.

Introduction

๐Ÿฆœ Welcome! This repository contains the documentation build pipeline for Solo Tech model finetuning as well as deployment for HuggingFaceโ€™s LeRobot SO-101. * ๐Ÿ  docs.getsolo.tech](https://docs.getsolo.tech/) is our docs home, centralizing finetuned Solo CLI models. This site is hosted on Mintlify. Follow the full installation guide or continue reading below:

Development

Install the uv package manager to acquire solo-server. The following block contains the full installation instructions.
curl -LsSf https://astral.sh/uv/install.sh | sh  
Create Python virtual environment, recommended Python version 3.12
uv venv --python 3.12
source .venv/bin/activate 
Choose one of the following for solo-server installation
  1. Install solo cli from PyPI python manager
uv pip install solo-cli
  1. Install solo cli from source
git clone https://github.com/GetSoloTech/solo-cli.git
cd solo-cli
uv pip install -e .

Solo commands

solo --help

Clone the repository

git clone https://github.com/GetSoloTech/solo-server.git
cd solo-server

Make the installation script executable

chmod +x install_mac.sh

Run the automated installation

./install_mac.sh

Next step