3D PRINT THIS ROBOT ARM, SHOW IT A TASK ONCE, AND IT LEARNS TO REPEAT IT
Show it a task once by moving a leader arm, and LeRobot trains it to repeat the action — the standard hardware behind Hugging Face's whole imitation learning ecosystem.
RoboticsAI
- difficulty
- ●●●●○
- time
- a week
- license
- Apache-2.0
- repo
- repo ACTIVE6,939 stars
●●●●○ · a week · Apache-2.0 · 6,939 stars · repo ACTIVE
WHAT YOU’LL NEED
- 3D printer + filament — printable parts — files are in the repo
- Electronic parts — full list with part numbers in the repo BOM
- Dev board / microcontroller — runs the project firmware
- Soldering kit + basic tools — one-time buy, serves every future build
Partner
COMPAREE VERDICT
This is the hardware backbone of Hugging Face's LeRobot project — you build a leader arm to demonstrate tasks and a follower arm that learns to mimic them. The promise is real: move the leader through a pick-and-place sequence, hit record, and the AI trains a policy to repeat it. The Robot Studio designed it specifically for imitation learning, and the whole LeRobot community uses this as the standard reference platform. The prints take days, the servo wiring is dense, and you will spend more time on motor calibration than the marketing suggests — but once it works, you have a genuine research-grade learning robot on your desk for a few hundred dollars in servos and filament. The single biggest trap is underestimating the software side: LeRobot is not plug-and-play, you need Python fluency and patience with dataset collection. If you have built a 3D printer from scratch and are comfortable with ROS or similar, this is a weekend-plus well spent. If servos and scripts intimidate you, start with a simpler arm first — this one assumes you know how to debug both.
IN THE REPO
NOT IN THE REPO
- —STL files, STEP models, and detailed assembly instructions all present in the repo.
- —Full bill of materials with servo specs, screws, and recommended suppliers.
- —Firmware and LeRobot integration documented — you will flash custom boards and run Python training loops.
- —Official Hugging Face assembly tutorial by Jess Moss is the single best starting point.
- —Apache 2.0 license — commercial use permitted.
- —What is missing: a one-click setup. You are building two physical arms (leader and follower), soldering servo controllers, configuring motor IDs, and debugging USB connections before any learning happens.
Can I build this?
Build at your own risk. Projects involve tools, electronics and sometimes mains voltage — follow the creator’s safety notes.
Partner · KickstarterHeyGears G1: 10M+ colors and transparent parts in one print, plus UV printing on flat objects. Figures, parts and labels — no painting.
Videos
Want to help with building robots?
No official YouTube channel from The Robot Studio or dedicated SO-ARM100 walkthrough. The Hugging Face tutorial by Jess Moss (linked in the repo README) is the best assembly guide — it is text and images, not video.
Gallery
Start here
Navigation into the creator’s own docs — we don’t rewrite the guide, we route you to the source.
- 1.Read the Hugging Face assembly tutorial by Jess Moss(Linked in the repo README — this is the clearest build walkthrough, with photos of every joint and servo placement.)
- 2.Check the bill of materials in /hardware/BOM.md(Exact servo model numbers and screw sizes — order everything before printing.)
- 3.Print the STLs from /hardware/STL(Leader and follower arms use the same parts — print two full sets. PLA is fine, PETG if you want more durability.)
- 4.Follow the LeRobot SO-ARM100 setup guide(In the LeRobot docs — this covers flashing the servo controllers, setting motor IDs, and running your first training loop.)
Resources
Documentation, files and community threads for this build — we link straight to the original sources and never rehost the creator’s files.
Partner · KickstarterCORE POWER BANK S: 0.2" thin, 2.8 oz, 5000 mAh with 22.5W fast charging. Semi-solid battery, carbon fiber, IPX7 waterproof.
KNOWN ISSUES
- Buying the wrong servos — the design expects Feetech SCS series with daisy-chain communication. Cheap hobby servos will not work.
- Underestimating the two-arm requirement — you need to build both leader and follower to do imitation learning. Budget double the print time and servos.
- Skipping motor ID setup — every servo needs a unique ID or the arm will twitch randomly. The LeRobot docs explain this, but it is easy to miss.
- Expecting instant learning — collecting a useful dataset means repeating a task dozens of times, then waiting for training to converge. First attempts often fail.
- Loose connections — the servo daisy chain is fragile. A single bad crimp will make the whole arm unresponsive.
- Ignoring the Python stack — LeRobot needs PyTorch, gym environments, and dataset tools. If you have never trained a policy before, budget a day just for software setup.
Can I build just one arm to test?
Yes, but you cannot do imitation learning without both — the leader is how you teach tasks. A single follower can run pre-trained policies if someone shares them.
What can it actually learn?
Pick-and-place, simple assembly, button presses — anything you can demonstrate repeatably in its workspace. Complex multi-step tasks need more data and tuning.
How long does training take?
Depends on the task and your GPU. Simple pick-and-place can train in under an hour on a decent GPU; more complex behaviours take longer and more demonstration examples.
Do I need a specific 3D printer?
No — any printer with a 200x200mm bed and decent accuracy works. The parts are not precision-critical, but loose joints will hurt learning performance.
Community builds
No community builds yet — be the first, we feature the best ones.
Discussion1
FROM THE COMPAREE TEAM
The repo has 6,905 stars and the whole LeRobot community runs on this hardware — if you have built one, what task did you teach it first?
The Robot Studio
The Robot Studio designed SO-ARM100 specifically as the standard hardware for Hugging Face's LeRobot project — a printable, reproducible platform so anyone could experiment with imitation learning without buying a $10k research arm. It became the default reference design for the whole ecosystem.
Keep building — related projects
Same category, picked by how close they are to this build.
FULL CADSO-ARM100: The Low-Cost Robot Arm Behind HuggingFace LeRobot
RoboticsAI●●●○○moderate
FULL CADXLeRobot: A Household Robot on an IKEA Cart
RoboticsAI●●●●○advanced
FULL CADYou can 3D-print your own walking Star Wars BD-X droid - fully open-source
RoboticsAI●●●●●expert
FULL CADOpenBot — turn a smartphone into a self-driving robot (3.4k stars)
RoboticsAI●●●○○moderate
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.
CompareeTEAM27d agoedited
Practical notes from our verification: the repo is clean and complete — STLs, BOM, assembly photos, and servo firmware all present. The Hugging Face tutorial is the best build guide, not a separate YouTube walkthrough. The single biggest surprise is how much time the software side takes — printing and assembly are straightforward if you have built anything with servos before, but getting LeRobot's training loop running and collecting a useful dataset is where most of the weekend goes. This is not a plug-and-play kit, it is a research platform — expect to read Python stack traces.