The development engine for physical AI
WendyOS and developer tools are free and open source.
Connect sensors. Develop and simulate. Deploy to real devices and improve your applications with data from the field.
Start with the hardware you have. Use Wendy Agent on Linux or Apple Silicon Mac, or run WendyOS on supported edge devices.
Jetson
Raspberry Pi
Dragonwing
Apple SiliconFrom an autonomous inspector to a portable fire-watch kit. See what people are building.
Community projectEUROPE EMBODIED Robotics Hackathon
A community team turned a Unitree Go2 into an autonomous facility inspector with ROS 2 and a Jetson Orin Nano. WendyOS ran the stack; Wendy Cloud connected the robot for remote access.
By Anirudh Jupudi, Adyansh Gupta & Manas Reddy Arumalla. Shared with the team’s permission.
Wendy productWendy Box · Portable fire detection
Full color and thermal cameras combine with local detection in one portable kit. Connected alerts help your qualified fire watch bring the wider team into the response.
Supports your qualified fire watch and existing site procedures.
Have an IP camera instead? Wendy can expose its network feed as a local Linux camera input, so your apps can read it without an SDK.
Build-loop benchmark: Cached Python build, upload, and run: ~200 ms. Timing varies by device, app, and connection.
From first build to next release
Wendy connects the work around your physical AI application, from its first sensor input to the next version running in the field.
Connect real sensors, iterate in your editor, and test with MuJoCo. Bring hardware into your workflow wherever it is.
Make a network camera a local inputShip signed software, control device access, and manage updates through local connections or Wendy Cloud.
Deploy the services your application needsInspect device behavior, collect aligned recordings, and use real-world data for analytics and model training.
Capture training data with TeleCollectOne engine, with connected tools for every stage.
Explore the Wendy platformPhysical AI in practice
From the lab to the factory floor, build applications that sense, decide, and act where the work happens.
Run quality inspection and monitor machines on the factory floor.
Put sensors and robots to work in demanding environments.
Deploy, test, and repeat on real hardware.
Process imaging and sensor data locally.
Keep perception and control running on the device.
From teams testing WendyOS and Wendy Box.
“If we found Wendy two years ago, we would have saved $4M in product development costs.”
CEO & Co-Founder
Autonomous farm & lawncare equipment
“I’m testing WendyOS on a Jetson to enable in-field AI to tune old, dumb control loops. I call it Automated Dynamic Local Loop Control.”
Automation Manager
Refinery production improvement
“We stopped tech projects because they weren’t practical or helpful — but in testing, the Wendy Box is a game changer. We’re already changing how we plan to run our crews.”
Site Manager
Turnaround resource management
Your first project
Choose a starting point. We'll show what you need, what to install, and the result to look for.
Add Wendy Agent and deploy a small Python API.
Keep your existing operating system.
Start on LinuxDeploy a native Swift example with Wendy Agent.
The native Mac target is in beta.
Start on my MacPrepare a supported board, discover it, and deploy a sample application.
Choose the setup guide for your hardware.
Start on my deviceRun a MuJoCo example and inspect its behavior before connecting a robot.
Docker required. No robot or GPU needed.
Start with a simulation