Pinned Tweet
The computer gave millions of people the freedom to create.
I want to help bring that freedom into the physical world.
At Structis, we're building a universal factory. Somewhere you can send a digital design and receive a finished, functioning product.
We're starting with robotic assembly. There is an enormous amount left to invent.
We're looking for the first people to build this with us.
People who think for themselves. Who care about the side of the fence nobody sees. Who are deeply optimistic about what humans can become capable of, and want to spend their lives contributing to it.
We're backed by Hustle Fund, Founders Inc, and Earthling VC.
We're forming the team in the Munich area.
If you've been looking for something worth giving yourself to, join us.
structis.ai/join-us/
We are growing our workforce!
New factory worker arrived for @StructisAI !!
Exciting times ahead. Universal Factory is getting closer and closer.
2
97
Grab one right here: structis.ai/hardware.html
First limited Batch 01 is live.
S1 Kit. Leader-follower. €3990.
Built in Germany.
4 kg payload, 700mm, cnc aluminium reinforced, backdrivable, LeRobot native.
Limited run
Order now!
structis.ai/hardware.html
LFG.
@StructisAI
3
540
Structis retweeted
Yesterday I hosted my The Garage event, directly in my garage lol.
many builders showed up, all firing with excitement about the new wave of robotics.
Pretty cool, will do more soon. 👀
trying to bring some of that california builder spirit to germany
Structis retweeted
Angel out, Bootstrapping is the way.
Selling the arms to fund the real thing. Ordering and price will be live soon!
Since it’s 3d print you can modify and repair them yourself.
@StructisAI
One of our first autonomous successes on the gland assembly.
How it works: we teleoperate the task first. That becomes training data for our model, which then attempts it autonomously. When it makes mistakes, we intervene and show it how to recover. Those corrections make the policy more robust and push the success rate up.
The model runs end to end, down to switching the screwdriver on and off.
Every task we run on the real robot grows the dataset. The bet: the more diverse it gets, the less data a new task needs.











