Overview
Complete guide to Wendy - the modern Physical AI operating system
Introduction
Wendy is the open source (Apache 2.0) operating system and toolchain for robots, drones, and edge AI. Inspired by the mobile development experience, Wendy lets you plug in an NVIDIA Jetson or Raspberry Pi over USB and start coding instantly. Wendy for Mac is in progress for teams that want the same deploy, manage, and debug workflow on headless Mac mini and Mac Studio targets.
Key features include:
- USB-C deployment and debugging — No internet or SSH needed. Just plug in and deploy.
- Remote Logging — Real-time logs from devices anywhere in the world.
- Atomic OTA Updates — Push updates to one or ten thousand devices without fear.
- VSCode Extension — Modern development experience with full debugger support.
- Apache 2.0 Open Source — No black boxes. Everything is open and hackable.
Developer Machine Setup
Supported Hardware
Wendy runs on edge devices with strong local compute. Plug one in over USB-C and start deploying.
NVIDIA Jetson
Orin Nano, AGX Orin
- Up to 2000 TOPS AI performance
- CUDA, PyTorch & MLX support
- Hardware video encode & decode
- Unified memory architecture
Raspberry Pi 5
Pi 5 (8GB recommended)
- Low power consumption
- Broad GPIO ecosystem
- Hardware PWM, SPI & I2C
- Affordable entry point
Core Components
Wendy consists of three main pillars:
WendyOS
The Apache 2.0 open source Linux distribution optimized for Physical AI. Includes a mobile-like USB-C development experience, remote debugging, and atomic updates.
Wendy for Mac
Headless Mac support for running wendy-agent on Mac mini and Mac Studio targets is in progress, bringing Wendy deployment and debugging to Apple Silicon machines.
Wendy Cloud
A fleet management solution for OTA updates, crash reporting, and remote telemetry. Built for teams scaling from prototypes to thousands of devices.
Developer Tools
CLI and VSCode extension for interactive breakpoints, hot reloading, and one-click deployment. Works with VSCode, Cursor, and Windsurf.
Wendy Frameworks
Performance-first Swift, Python, and Rust frameworks for running AI models, controlling I/O, and handling high-speed telemetry.