
Your Physical AI Partner
Hardware
All Robots and Devices. One Platform
Each Dexmate robot ships with the same software foundation, ready to operate from day one.


End Effectors
Bimanual Dexterity
Two 7-DoF arms work together on two-handed tasks a single-arm rig can't handle.
High-payload Arms
Designed for heavy-duty manipulation with consistent accuracy in any pose.
Detachable Vision
Easily attach a camera to provide more close-distance vision for manipulation.
Self-Locking Hold
Holds a part indefinitely without overheating, and keeps its grip if power drops.
7 ft 2 in
Large workspace, floor to 7 ft 2 in (2.2 m)
10+ lbs
High payload per arm, any pose (5 kg)
20+ h
Long operation time
24+ DoF
Handles bimanual dexterity & mobility tasks
60 N
Grasping force, the same on DexGripper S & D
55°
Max opening angle for coupled jaws
10.3 in
Gripper length, closed (262 mm)
2.2 - 3 lbs
Weight: 1.0 kg for DexGripper S; 1.4 kg for D
Who It’s For
One Platform, Every Physical AI Application





Robotics Experts
"Simulation cannot provide the level of variability we see in actual physical manipulation. For collecting real data and making policies autonomous, you have to have a robot system like Vega."

Kevin Lynch
Professor of Mechanical Engineering, Northwestern University
Developers & Researchers
"Before Vega, we didn't have a robust platform to test our ideas and deploy our models. With Vega, we can easily bring those ideas to real robots and let them explore the real world."

Yue Wang
Physical Superintelligence (PSI) Lab, USC
Physical AI Companies
"Vega's long arm reach, articulated torso, and mobile base give us the workspace and flexibility to tackle a wide range of manipulation tasks, all at a reasonable price. Building on that capable platform lets us concentrate our engineering effort on data, models, and deployment platform, while saving the time and complexity of developing the hardware stack from scratch."

Hyungmok Son
Co-founder & CTO, Config
Data Companies
"Vega gives Lightwheel RoboStack a production-ready physical platform out of the box. Instead of spending cycles on robot integration and low-level control, we can focus on policies, evaluation, and getting real-world deployments working."

Jay Yang
Chief Architect of Lightwheel
System Integrators
"Our collaboration with Dexmate allows us to use a physical robot platform like Vega to reduce the time and cost of building hardware and basic control capabilities from scratch, and evaluate real-world applications in logistics and manufacturing more efficiently."

Dongshin Son
LG CNS Future Robotics LAB
Trusted Clients






FAQ
Common Questions
A Vega 1 Pro or Vega 1 U, assembled and tested, plus the software to program it. That means Python, C++, and Rust APIs, the SDK, and SimReady URDF and USD models of your exact robot. End effectors are ordered separately.
Yes. Vega 1 Pro and Vega 1 U run the same software, so code written for one runs on the other. Vega 1 U also shares Vega's upper-body kinematics, so data collected on a bench carries straight over to the mobile robot.
Nothing is locked in. Train with your own models and pipeline, and test in the simulator you already use. Mount your own end effectors on the published mechanical and electrical interfaces.
No autonomy is bundled. Position control, safety checks, and the sensors work out of the box. The task behavior is what your team builds on top.
An operator drives the robot in VR or with the open-source exoskeleton kit, in the space where the skill will run. Each session is recorded as training data for imitation learning. The same setup lets a person take over whenever a task needs a human.
It's built for them. We build for research labs, frontier AI labs, developers, and industrial application teams. The hardware is made to hold up to daily use.
Order from our store, or talk to the team about your use case first. Vega 1 U is the faster start on a bench. Vega 1 Pro adds the mobile base, the adjustable torso, and the full reach.
Published papers from labs including UC Berkeley, Stanford, USC, Carnegie Mellon, UIUC, NVIDIA, Google DeepMind, and Amazon FAR ran on Vega. They are collected under Research Papers, and our own writing is on the Blog.
Start Your Physical AI Journey with Us
