From demo to deploy
Robotics deployment is hard enough. We help you go from a demo to a successful deployment.
What is blocking your deployment?
Each card below is an example pipeline — run it as-is, fork it, or describe your own and the agent builds the recipe. Our goal is getting you deployed faster.
At the edge, every bit, ounce, watt matters.
Getting a base model onto your robot — small enough, fast enough, cheap enough, good at the job — takes more than one pass. Haptic runs the loop for you.
OpenVLA-7B · compression path
Model size
14.0 GB
Accuracy (LIBERO-Spatial)
97.0%
model
FP16
We build in public.
We build in the open and are open-source first, so the best way to get to know us is to read our tech blog or check out our GitHub. We'd love to hear from you.
The Hardest Part of Shrinking a Robotics Model
Shrinking Pi0.5 by 2.9× on disk and 2.8× faster. The paper gives you the recipe; the pipeline tax is what makes it hard in production.
The Software-First Robotics Founder
Software-first founders are entering robotics with different assumptions, different problems, and different expectations. Here is what we are hearing.
There Is Plenty of Room (and Pain!) in Physical AI Research
To inspire builders, here is a list of problems that keep coming up again and again in physical AI research papers.