Install Wendy

Install Wendy CLI

Install this on your developer machine or continuous integration machine.

macOS / Linux

curl -fsSL https://install.wendy.dev/cli.sh | bash

Windows

winget install WendyLabs.Wendy --source winget

Install `wendy-agent`

Install this on an existing Mac or Linux target. WendyOS images already include it.

Linux

curl -fsSL https://install.wendy.dev/agent.sh | bash

Mac (beta, Apple Silicon)

brew tap wendylabsinc/tap
brew trust wendylabsinc/tap
brew install --cask wendy-agent

Read the Mac installation guide

Get started

Quickstart

Build apps

Connect Wendy to ChatGPT Chat with your hardware Persistent agents and A2A Send notifications from a device app Adjust Camera Exposure Stagefile Multi-App Deployments Build Once, Deploy to Several Devices AI Coding Agent Setup

Hardware

Hardware overview Camera Access Microphone Access Speaker Access Bluetooth Access GPU Access

Debug & observe

Wendy Data VSCode Extension Troubleshoot your first deployment Frequently Asked Questions

Deploy & manage

Cloud

Robotics

Robotics overview Unitree robot simulators Sim to real with robot simulators Unitree G1 Reflash Unitree G1 PC2 Wendy for ROS 2 Robot diagnostics with MCP Wendy for Foxglove

Concepts

Reference

Release Process Roadmap Status

GitHub Discord

Detailed reference

Vscode

WendyOS developer documentation.

View raw Markdown Agent docs index

PKI

Wendy uses mutual TLS (mTLS) to authenticate both devices and CLI clients against the agent's gRPC server. Certificates are issued by a CA managed by either Wendy Cloud or a self-h

Wendy Lite

Wendy Lite is Wendy's runtime and deployment layer for ESP32 microcontrollers. It supports native ESP-IDF applications as the recommended project model and can also run portable WA