Supported hardware
WendyOS ships ready-to-flash images for the boards below. Every supported board is built and published nightly from our open CI, so images stay current with the OS — no waiting for quarterly releases.
| Device | SoC | Boot storage | AI acceleration | Status |
|---|---|---|---|---|
NVIDIA Jetson Orin Nano Our primary target — the board behind Wendy Box. | Tegra234, 8GB | SD card or NVMe | CUDA, TensorRT, optional DeepStream | Available |
Raspberry Pi 5 | BCM2712, 8GB | SD card or NVMe | — | Available |
Raspberry Pi 4 / 3 | BCM2711 / BCM2837 | SD card | — | Available |
NVIDIA Jetson AGX Orin Built nightly; general availability soon. | Tegra234, 64GB | eMMC or NVMe | CUDA, TensorRT, optional DeepStream | Beta |
NVIDIA Jetson AGX Thor | Tegra264 (JetPack 7) | NVMe | CUDA 13 stack | In progress |
QEMU ARM64 For development and CI without hardware. | Emulated | Virtual disk | — | Dev only |
Every board gets the same experience
USB-C host mode for cable-only development, mDNS discovery with wendy discover, the containerized app runtime, entitlement-gated hardware access, and one-command deploys with wendy run. On Jetson, images additionally include A/B OS updates with automatic rollback and the full NVIDIA stack — CUDA, TensorRT, and optional DeepStream — pre-wired for GPU containers.
Want a board that isn't listed? Tell us what you're building or open an issue on GitHub.
Ready to build on WendyOS?
WendyOS is the open-source operating system for Physical AI — deploy your apps to NVIDIA Jetson, Raspberry Pi, and more in seconds, over USB-C, wireless, or the cloud.