Built for coding agents

Build physical AI with your coding agent.

Wendy is the open-source OS and toolchain that gives Claude Code, Codex, and other coding agents a fast, reliable, and repeatable way to ship to robots, drones, and edge devices. Your agent deploys over USB-C, your network, or the cloud, and a provisioned device takes commands only over mutual TLS.

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

Runs on

  • NVIDIA
  • Qualcomm
  • Ubuntu
  • Raspberry Pi
Unit viewwendyos-zestful-stork.local
Coding agent

Example session: a coding agent is asked to make a Unitree Go2 wave and then patrol. It starts wendy run --watch, which deploys the greeter app to the robot over USB-C, then edits main.py twice. Each edit redeploys in a few seconds, and the second one starts the dog navigating a route of four waypoints.

01Agents

Every Wendy customer builds with a coding agent.

Claude Code and Codex install the Wendy plugin, and Cursor, Windsurf, and Claude Desktop connect through the Wendy MCP server. Your agent sets up the device, deploys the app, reads the logs, and fixes what broke, using the same commands and authenticated connections you do.

  • 01 · Fast

    Test every edit on the device.

    A Stagefile rebuilds a Python edit in under 200 ms, and Wendy sends only the chunks the device is missing, so each edit is running on the hardware within seconds. Your agent sees the result as the logs stream back.

    • wendy run --watch
  • 02 · Reliable

    Output an agent can parse.

    When no terminal is attached, most CLI commands answer in JSON, and the CLI stops with a clear error instead of waiting on a prompt. MCP results are size-capped, with a hint on how to narrow the query.

    • wendy discover --json
  • 03 · Repeatable

    One manifest for every deploy.

    wendy.json declares the app and the hardware it may use, checked against a published schema. The same project deploys the same way from your agent, a teammate, or CI.

    • wendy json validate
  • 04 · Secure

    Guardrails the agent works inside.

    Your agent works through the Wendy API, which a provisioned device serves only over mutual TLS, and release Jetson and Raspberry Pi images have no SSH server. The CLI refuses a device whose identity doesn’t match, apps get only the hardware wendy.json declares, and every MCP tool is tagged read-only, mutating, or destructive.

    • mTLS
    • device pinning
    • entitlements
Connect your agent

claude plugin marketplace add wendylabsinc/wendy-agentic-coding

claude plugin install wendy-agentic-coding@wendy-agentic-coding

Then run /reload-plugins and start with /wendy-agentic-coding:wendy-install.

Then ask your agent

Find my Jetson, deploy the camera-feed-yolo template, and tell me what the camera sees.

Coding agent setup guide
What your agent can do44 MCP tools
  • Find devices over USB-C and your network
  • Build, deploy, and restart apps
  • Read logs, metrics, and traces
  • Sample ROS 2 topics and LiDAR
  • Capture a camera frame
  • Join Wi-Fi and pair Bluetooth
  • Update the OS and confirm the result
  • Tunnel to remote devices (Cloud beta)
02Link

Your coding agent calls the wendy CLI, which builds the app into a container, finds the device, and sends only the chunks the device is missing. Logs stream back over the same link, so the agent sees what the device sees.

Your computer

wendy CLI

  • macOS (Apple Silicon), Windows, or Linux
  • Plugin for Claude Code and Codex
  • MCP server for Cursor, Windsurf, and more
MacBook Pro
  1. USB-C

    Plug in one cable. The device appears as a USB network adapter at a fixed link-local address, so there is nothing to set up on your laptop.

  2. Local network

    Each device advertises a readable name, like wendyos-zestful-stork.local, over mDNS.

  3. Wendy CloudBeta

    Enrolled devices dial out, so there are no inbound ports or static IPs to manage.

Your device

Wendy Agent

  • Runs your apps in sandboxed containers
  • Built into WendyOS for Jetson, Raspberry Pi, and Dragonwing
  • Or installed on any arm64 or x86_64 Linux, or a Mac (beta)
Quadcopter
  1. Step 01

    $ wendy install

    Flash WendyOS from your laptop with its Wi-Fi, name, and optional Wendy Cloud enrollment set in the same command, or add the agent to a Linux machine you already run.

  2. Step 02

    $ wendy init

    Scaffold an app from a template, or bring any project with a Dockerfile. Add --assistant claude or codex to hand the new project to your agent.

  3. Step 03

    $ wendy run

    Build, deploy, and stream logs in one step. With --watch, every change your agent saves redeploys.

03System

Everything between your code and the hardware.

Wendy covers the work that sits between a working prototype and a device in the field, with one toolchain from the first build to the fleet.

Develop01 / 07

Use the languages, editors, and coding agents you already know.

Write Python, Swift, Rust, TypeScript, or C++, start from a template, or bring any project with a Dockerfile or Compose file. Hand a new project to Claude Code or Codex with one flag, or work in VS Code or Cursor with the Wendy extension.

Read the docs

$ wendy init --template# start from a sample app

$ wendy init --framework ros2# ROS 2 project

$ wendy init --assistant claude# hand off to Claude Code

04Units

Runs on the hardware you already have.

Flash WendyOS to a supported board, or install Wendy Agent on the Linux computer or Mac you already run.

05Field reports

Built with Wendy.

A community robot, our own field hardware, and notes from teams piloting WendyOS today.

Archive 01Community project
Autonomous inspection presentation on stage at the EUROPE EMBODIED Robotics HackathonEurope Embodied hackathon

An autonomous Go2 inspector.

A community team turned a Unitree Go2 into an autonomous facility inspector with ROS 2 and a Jetson Orin Nano. WendyOS ran the stack, and Wendy Cloud connected the robot for remote access.
  • ROS 2
  • NVIDIA Jetson
  • Unitree Go2

By Anirudh Jupudi, Adyansh Gupta, and Manas Reddy Arumalla. Shared with the team’s permission.

Archive 02Wendy product
Yellow Wendy Box portable kit with a protected camera windowWendy Box

Portable fire watch, with local detection.

Full color and thermal cameras combine with on-device detection in one portable kit running WendyOS. Connected alerts help your fire watch bring the wider team into the response.
  • Thermal imaging
  • Local AI
  • Battery powered

Supports your qualified fire watch and existing site procedures.

  • Transmission 01Received
    Established robotics company
    “If we found Wendy two years ago, we would have saved $4M in product development costs.”

    CEO & Co-Founder

    Autonomous farm and lawncare equipment

  • Transmission 02Received
    Fortune 50 oil company
    “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

  • Transmission 03Received
    Fortune 500 construction company
    “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

06Operations

Deploy where the work happens.

Teams use Wendy to run perception, inspection, and control on devices far from a data center, including places with no network at all.

07Proposal
ProposalAwaiting input

Point your coding agent at a real machine today.

Install the Wendy CLI, add the Wendy plugin to Claude Code or Codex, and ask your agent to deploy a sample app to your hardware. You can also start with a MuJoCo simulation if you don’t have a robot yet.

Install the CLI
curl -fsSL https://install.wendy.dev/cli.sh | bash
For teams

Planning a pilot or a fleet?

Talk with our engineers about your hardware, security review, and rollout. We also build and ship field-ready devices like Wendy Box.

WendyOS
Free · Apache 2.0
Wendy Cloud
Beta
Support
Pilots and fleets

Ask Wendy

Answers about Wendy and WendyOS

What would you like to know?

Ask about devices, development, and deployment.

Check linked docs for technical details.