A 299-DOLLAR OPEN-SOURCE DESKTOP ROBOT THAT PLUGS STRAIGHT INTO HUGGING FACE'S AI MODELS
A 30 cm desktop robot with a six-degree-of-freedom head, a rotating body, two expressive antennas, a wide-angle camera and direct access to Hugging Face's AI models.
RoboticsAI
Built withRaspberry Pi
- difficulty
- ●●●○○
- time
- a few hours
- license
- Apache-2.0
- repo
- repo ACTIVE1,534 stars
●●●○○ · a few hours · Apache-2.0 · 1,534 stars · repo ACTIVE
WHAT YOU’LL NEED
Jump to section
COMPAREE VERDICT
Reachy Mini is for someone who wants to prototype social robotics or AI agent embodiment without machining a single part. You buy the kit, bolt it together in 2-3 hours, install the Reachy Mini Control app, and you have a desktop head that can track faces, run vision models, and speak. The Hugging Face integration is real — the SDK and app store connect the robot to models on the Hugging Face hub — but most of those models will not run usefully on the onboard Raspberry Pi CM4, and the ones that do still need you to write Python to wire them up. The assembly itself is straightforward: the kit takes about 2 to 3 hours with the step-by-step guides. The hardest part is not the build, it is deciding what you actually want the robot to do and then writing or adapting the code to make it happen. If you want a platform to learn embodied AI and you are comfortable in Python, this is excellent. If you expect the kit to arrive doing something impressive out of the box, you will be disappointed — the demos exist, but you will spend time configuring dependencies and tuning behavior. The single thing most likely to go wrong is underestimating how much software work stands between you and a demo that feels alive. The hardware is solved; the interaction layer is yours to build.
IN THE REPO
GOOD TO KNOW
- —This is a kit product, not a scratch build — you buy the mechanical parts and electronics from Pollen Robotics, then assemble.
- —The repository contains the Python SDK, simulation files, and documentation. Hardware CAD (STEP files) is linked separately.
- —The repo contains the Python SDK, the daemon and examples; motion uses off-the-shelf Dynamixel XL330/XC330 servos.
- —SDK is Apache-2.0. Hardware design files are Creative Commons BY-SA-NC — attribution and share-alike, no commercial use.
- —The 299-dollar price is for Reachy Mini Lite (USB to your computer). The Wireless version, with a built-in Raspberry Pi Compute Module 4 and battery, costs more.
- —The Reachy Mini Control app and Python SDK run on Windows, macOS and Linux.
Parts to buy
2 itemsFrom our check of the build. Exact quantities and part numbers are in the creator’s BOM.
Can I build this?
Build at your own risk. Projects involve tools, electronics and sometimes mains voltage — follow the creator’s safety notes.
Videos
Testing Hugging Face's Raspberry Pi-powered open source robot
Jeff Geerling's hands-on test. For the build, Pollen Robotics publishes official assembly videos for both the Wireless and Lite versions.
More builds like this
All projectsGallery
Start here
Navigation into the creator’s own docs — we don’t rewrite the guide, we route you to the source.
- 1.Order the Reachy Mini kit (Choose Lite (USB to your computer, wall-powered) or Wireless (onboard Raspberry Pi CM4, battery and Wi-Fi) depending on whether you want a tethered or standalone robot.)
- 2.Read the assembly guide (Online guide with short video clips for every step, plus the official assembly video.)
- 3.Install the app and SDK (Install the Reachy Mini Control app (Windows, macOS, Linux); the Python SDK installs with pip or uv.)
- 4.Run the Hello World demo (Simple Python scripts to move the head and display expressions.)
Resources
Documentation, files and community threads for this build — we link straight to the original sources and never rehost the creator’s files.
KNOWN ISSUES
- Buying the kit expecting a finished demo robot — you get the hardware platform and SDK, the behavior is yours to code.
- Underestimating the gap between the huge number of Hugging Face models and the few that run at usable speed on the Wireless version's Raspberry Pi Compute Module 4 (4 GB RAM) — heavier models run on your computer or in the cloud.
- Not reading the SDK examples before ordering — if the Python API does not make sense to you, the hardware will sit unused.
- Assuming the Hugging Face integration is plug-and-play — it gives you API access, you still write the Python to load models, process camera frames, and synthesize responses.
What is the difference between the Lite and Wireless versions?
Reachy Mini Lite connects to your computer over USB and is powered from the wall. The Wireless version has a Raspberry Pi Compute Module 4, a battery and WiFi built in, so it runs on its own. Wireless costs more.
Can I run this on Windows or macOS?
Yes. The official Reachy Mini Control desktop app runs on Windows, macOS and Linux, and the Python SDK installs with pip or uv. Some ARM64 machines and unusual Linux distributions may need the command-line route instead of the app.
What AI models actually run well on this?
Lightweight vision models (MobileNet-scale), small language models (up to a few billion parameters quantized), and cloud-offloaded APIs. Do not expect to run Llama 70B locally.
Is there a community or forum?
Pollen Robotics has a Discord linked from their main site. The GitHub issues are active for SDK questions.
Can I add arms or a mobile base?
Reachy Mini has no arms: it is a head on a six-degree-of-freedom Stewart platform, a rotating body and two antennas. The hardware design files are open (CC BY-SA-NC), so you could design your own base or add-ons, but nothing like that is provided.
Community builds
No community builds yet — be the first, we feature the best ones.
Discussion1
FROM THE COMPAREE TEAM
Most Reachy Mini apps are web apps that drive the robot from a browser, and the Wireless version runs on a Compute Module 4 on board. What would you actually build with it — a local agent, a cloud-backed assistant, or something else?
Pollen Robotics
Pollen Robotics is a French company building open-source humanoid robots for research and education. Reachy Mini is the desktop version of their full-size Reachy robot, designed to make expressive robotics accessible without a lab budget.
Keep building — related projects
Same category or platform, picked by how close they are to this build.
FULL CADYou can 3D-print your own walking Star Wars BD-X droid - fully open-source
RoboticsFor expert builders
NO CAD FILESThis robot watches your hand move and puts a sweet in it — code is public
AIFor expert builders
FULL CADXLeRobot: A Household Robot on an IKEA Cart
RoboticsFor advanced builders
FULL CAD3D print this robot arm, show it a task, and it learns to repeat it
RoboticsFor advanced builders
FULL CADOpenBot — turn a smartphone into a self-driving robot (3.5k stars)
RoboticsFor intermediate builders
NO CAD FILESOne camera, one brain — and this robot dog taught itself parkour
RoboticsFor expert builders
DISCLAIMER
- Comparee is not the author of the projects featured here. All rights to each project belong to its creator — every page links to the original source, and we never host creators’ files.
- Information is provided without warranty and may become outdated as projects evolve. Prices are indicative bands only — always check the creator’s parts list for current costs.
- Building and operating any project is at your own responsibility. Protective equipment, safe workshop practice and compliance with local regulations are the builder’s responsibility.
CompareeTEAM2mo agoedited
Practical notes from our verification: the repository is actively maintained, with SDK updates, example apps and tutorial notebooks. Reachy Mini is sold as a kit that takes about 2 to 3 hours to assemble, and there are step-by-step guides on the Hugging Face docs plus assembly videos, so the build itself is well covered. The Wireless version runs on a Raspberry Pi Compute Module 4 with a battery; the Lite version is driven over USB from your Windows, macOS or Linux computer. The software is Apache 2.0, while the hardware design files are under Creative Commons BY-SA-NC, so the hardware cannot be used commercially. The Hugging Face integration is real but not magic: there is an app store and a Python and JavaScript SDK, but you still write the code that links a model's output to the robot's movements or speech. There is an active Discord for help. Correction (4 October 2026): we re-checked this page line by line against the project's own repository, documentation and videos, and fixed errors in earlier versions.