Digital Brains

The boards that can actually think.

A robot is only as capable as the mind you give it. This is a directory of maker boards that can run Physical AI models — grouped by the role they play on the machine, from a few-dollar microcontroller to an edge-AI module that runs a full vision-action policy.

The one rule

It has to run a real policy.

The gate for this directory is simple and strict: can it run a genuine Physical AI model — perception, or a learned policy — either on-device or by pairing with one that does? A robot locked to canned, pre-scripted behaviors is a toy, not a substrate. Every board here clears that gate.

Three tiers by role

Brains, reflexes, and accelerators.

You don't need the biggest board — you need the right one for the job. Most real builds combine a couple: a main brain, cheap reflexes, and sometimes a bolt-on accelerator.

Main brain

Vision-action brains

Linux-class boards with enough compute and memory to run real perception, and — at the top — a full vision-action policy on-device, no laptop tether.

Reflexes & eyes

Tiny-ML microcontrollers

Cheap, low-power boards that run tiny models and drive the motors. Often the 'eyes' or reflexes paired with a Tier-A brain, or offloading heavy perception to a phone or laptop.

Add-on acceleration

Accelerators & FPGA co-processors

Bolt-on compute: an M.2 NPU that takes the neural load off the main board, or an FPGA fabric for hard real-time sensor and motor work a CPU does poorly.

The line worth knowing

Vision is cheap. A real VLA is not.

Almost every low-cost NPU here — Hailo-8, Coral, the Rockchip and Kendryte engines — is an INT8 vision accelerator: excellent at detection, pose, and segmentation, but it won't run a full transformer vision-action model on the accelerator itself. A true on-device VLA needs a GPU-class brain (Jetson Orin or Thor) or an LLM-capable NPU with its own DRAM (Hailo-10H). Below that line, the policy runs on the host CPU while the NPU feeds it eyes — which is plenty for most maker builds.

Tier A · Main brains

Full Linux-class boards.

The mind of the robot. The top of this tier runs a real vision-action policy on-device; the rest run rich perception and small or distilled policies.

NVIDIA Jetson AGX Thor

Blackwell GPU · 128 GB · 2,070 FP4 TFLOPS · $3,499

The humanoid brain — runs large VLAs on the robot. Overkill for a simple rover.

NVIDIA Jetson Orin Nano Super

Ampere GPU · 8 GB · 67 INT8 TOPS · $249

The default autonomous-robot brain: real-time vision, VLMs, distilled policies, the most mature edge-AI stack.

Radxa Rock 5 (RK3588)

8-core Arm · up to 32 GB · 6 TOPS NPU · ~$150

Best-value full-Linux main brain; runs YOLO well and small LLMs/policies. Add an NPU for heavy nets.

Raspberry Pi 5 + AI HAT+

Quad Cortex-A76 · Hailo 13–26 TOPS · $80 + $70–110

The most familiar Linux brain with a bolt-on vision accelerator and the biggest community.

Particle Tachyon

Qualcomm QCM6490 · ~12 TOPS · 5G + Wi-Fi 6E · $249

A connected edge brain for when the robot needs its own cellular link, not just perception.

BeagleY-AI

TI AM67A · 4 GB · 4 TOPS · $70 · OSHWA-open

The most-open main brain; multi-framework (ONNX + TFLite) on fully-published hardware.

CanMV-K230

Dual RISC-V · ~6 TOPS KPU · ~$49

The cheap RISC-V vision brain / smart camera; MicroPython + OpenMV, real on-device detection.

Tier B · Reflexes & eyes

Microcontroller-class boards.

Cheap, low-power, and tiny. Great as a robot's 'eyes' or reflexes — and the honest home for boards that teach embedded skills but can't host a policy.

Espressif ESP32-P4 / S3

Dual RISC-V or Xtensa + SIMD · camera + ISP (P4) · $3–50

Smart-camera 'eyes' and tiny-robot reflexes; runs detection/pose on the CPU, feeds a bigger brain.

Raspberry Pi AI Camera (IMX500)

On-sensor neural accelerator · 8 MB · $70

Inference runs inside the sensor — only the result crosses the wire, so the host CPU stays free.

Milk-V Duo (SG2002)

RISC-V + Arm + ~1 TOPS TPU · $8

A pocket Linux + NPU node — cheap actuation and light vision at the edge of a bigger build.

LuckFox Pico (RV1106)

Cortex-A7 + ~1 TOPS NPU + ISP · $14+

Thumb-sized perception co-processor for small detection where space and power are tight.

uFerris (XIAO ESP32-C3)

Single-core RISC-V · 160 MHz · Wi-Fi/BLE · $25

A Rust-on-embedded teaching board — reflexes, comms, and the on-ramp to embedded Rust. Not an AI brain: pair it with a Tier-A brain for the policy.

Tier C · Accelerators & FPGA

Co-processors, not standalone brains.

Bolt these onto a host: an M.2 NPU for heavy nets, or an FPGA fabric for hard real-time sensor and motor work.

Hailo-10H (M.2)

40 INT4 TOPS · own 4–8 GB DRAM · ~$130 (Pi AI HAT+ 2)

The on-device LLM/VLM/VLA accelerator — its own memory lets a modest SBC run a real policy without a Jetson.

Hailo-8 (M.2)

26 TOPS INT8 · ~$70–220

A high-FPS vision front-end (detection, pose, segmentation) bolted onto a Pi- or x86-class host.

SparkFun Alchitry Au / Cu

Artix-7 FPGA ($150) / iCE40 FPGA ($54, fully-open flow)

Deterministic real-time: sensor sync, motor commutation, and small custom quantized-NN fabric a CPU can't hit.

Google Coral / Edge TPU

4 TOPS INT8 · TFLite-only · end-of-life

Legacy — flagged, not recommended for new designs. Prefer Hailo or BeagleY-AI.

Specs and prices verified July 2026 and kept current. Have a board that belongs here? Tell us →