A home for your robot's digital twin

Your CAD assembly, alive in physics — before you buy a single part.

Twinhaven turns a SolidWorks assembly into a physics model you can run, record, measure and compare. See the overloaded joint, the clearance that closes, the motion that drifts — while it is still cheap to change.

Every core idea is built and proven in working prototypes. Now we are shaping them into one coherent product — early users shape what ships first.

Concept illustration of Twinhaven measurements, stroboscope and run timeline.

Robots are designed across disconnected tools

CAD, physics, electronics, control code, training data — each hand-off is manual, so every iteration costs days. Twinhaven closes the seams. Our metric is the cost of one iteration: from “moved a motor in CAD” to “saw the new graphs” in minutes, not days.

How it works

The tools you already use stay where they are. Twinhaven connects them into one project — one digital twin of the whole machine, with every change on record.

works todayon the roadmap CAD geometry, joints, parts EDA motors, drivers, wiring Blender looks, lights, cameras Twinhaven project one digital twin of the whole machine Physics · contacts, motors, sensors Behaviour · control code in Python Run record · every step, replayable runs on your machine · scales to the cloud Measure & decide ✓ stroboscopes, graphs, limits Data & training labelled datasets, AI Real hardware same logic on the controller roadmaproadmaproadmaproadmap Git · the full history of the whole machine — design, code and runs

Swipe the scheme sideways →

Wiring, inside the same twin

concept · on the roadmap

A hexapod as an example: six legs, a head and an arm talk to the controller over buses through the body. Each wire becomes a signal in the simulation.

coxafemurtibia servo bus I²C sensors USB video Leg L1Leg L2Leg L3 Leg R1Leg R2Leg R3 ID 1–3ID 4–6ID 7–9 ID 10–12ID 13–15ID 16–18 Head camera · pan servo Controller your Python logic Body bus hub · power · IMU bus A → left · bus B → right IMU on I²C · battery 2S Arm 2 joints · gripper · bus C ● command ○ feedback …and the same buses on the bench — to debug and tune real hardware Twinhaven the twin and your logic USB Adapter speaks servo bus · I²C commands readings Real Leg R1 on the bench · others simulated For bench debugging and tuning: swap one block for the real one, the same commands drive it, its readings land next to the simulated ones.

Today the twin already runs the legs, motors and your control code. Drawing the wiring as a schematic and simulating it is the next feature; the hardware adapter follows it on the roadmap.

Analysis tools — exhaustive by design

Every run is recorded. The timeline takes you to any moment in one move — scrub, loop a fragment, lay a reference run next to today's. Three kinds of instruments read the record.

Todayrun · 2 h 14 min · 3,2 M steps — gaps fold the quiet stretches, fragments name what matters
Today

Motion — stroboscopes

Freeze poses over time into one 3D picture: the path, the swing, the moment two parts come closest. Compare the motion of two design versions side by side.

Today

Motion, measured — graphs

Clearances, distances and angles become graphs over the whole run, with limits, a pass / fail verdict on every step, and the worst moment one click away.

Roadmap

Physics — forces and torques

Instrument stands for the whole machine: joint torques, motor currents and power, contact forces — gauges and limits that show which motor is overloaded and when, before it is ordered.

Why each piece is there

A robot is mechanics, electronics, code and data at once. Each piece below answers a question that is expensive to answer with metal.

CAD — the shape of the truth

Your assembly stays the single source of geometry. Parts become bodies with real masses; change a part in CAD and the twin follows — no remodelling by hand.

Physics — answers, not animation

Built on MuJoCo, the physics engine trusted in robotics research. Contacts, motor torque and friction are computed, so a joint overload shows up before you order the motor.

Roadmap

EDA — mechanism meets circuit

A motor is a mechanical part and an electrical load at the same time. Linking the schematic to the mechanism checks drivers, currents and power before the board is made.

Roadmap

Blender — for complex sensors

Cameras, lidars and thermal sensors need light, materials and weather, not just geometry. Blender renders what the robot's sensors would actually see — including fog and glare.

Behaviour — the same logic as on the robot

Control code is plain Python behind the schematic. It drives the twin today, so you debug logic without risking hardware; carrying the same logic to the real controller is on the roadmap.

Git — a time machine for the whole design

Git is the version system every software team relies on. Twinhaven brings it to the entire machine: every design change and every run is kept, any result from months ago can be replayed, and a team works in parallel without overwriting each other.

Roadmap

Data & AI — not a weekend job

Teaching a robot to see or walk takes thousands of simulated runs with varied light, weather and loads, and labels for every frame. That is real infrastructure — compute farms and pipelines — which Twinhaven runs in the cloud so you don't have to build it.

Measurements — a verdict, not a guess

Set a clearance or an angle with limits and every step of a run gets pass or fail, with the worst moment one click away. Engineering decisions get a number behind them.

Local and cloud — your data, your choice

Design and debugging run on your machine, so your CAD model does not have to leave it. Heavy work — mass simulation, data generation, training — scales out to the cloud when you need it.

What works today

A working prototype — not mock-ups. This is what already runs.

Today

From assembly to physics

Bring a SolidWorks assembly in: parts become bodies, joints are set from the assembly — mates suggest axes and limits. Out comes a standard MuJoCo model.

Today

Run, record, rewind

Every run is recorded on a timeline. Scrub back to any step, play fragments in a loop, keep the record across restarts.

Today

Measure with limits

Put a clearance or an angle between faces and bodies, set the limits, and get a pass / fail verdict on every step of the run — with the minimum and maximum one click away.

Today

Stroboscope

Freeze poses over time into one 3D picture: see the trajectory, the swing and the moment two parts come closest.

Today

Compare against a reference

Keep a run in git as a reference and lay today's run next to it — what changed after your design edit is visible at a glance.

Today

Your data stays yours

The project lives in your own git repository, the output is open MJCF. Your CAD model does not have to leave your machine.

Built for engineers who ship machines

Mechanical & mechatronics engineers

Check reach, clearances and joint loads before ordering parts. The most expensive mistake is the one found after assembly.

Robotics teams

One model shared by design, electronics and software — instead of three copies drifting apart.

Researchers & students

Get a clean MuJoCo model of your own hardware straight from CAD — then use any open-source library you like.

Open core: the engine is a gift, the workflow is the product

The path from CAD to physics is free, open and local. The tools that make a whole product work — electronics, behaviour, rendering, data — come as Pro features.

Free & open
  • CAD bridge and MJCF compiler
  • Local physics and rendering runtimes (MuJoCo, Blender)
  • Open protocol and Python scripting
  • Core timeline, measurements and stroboscope
Pro · on the roadmap
  • Devices, wiring and behaviour code in your IDE
  • Photoreal rendering on demand
  • Synthetic datasets and training
  • Teams, history and advanced analysis

Roadmap

Order, not dates. Early users decide what comes first.

Now

SolidWorks

Assembly import, timeline, measurements, stroboscope, references.

Next

More CAD & electronics

Autodesk Inventor, then Fusion, Onshape and STEP. Devices, wiring and behaviour code.

Later

Render, data, training

Photoreal frames, synthetic datasets, training in simulation and transfer to hardware.

Join the waitlist

We will email you once — when Twinhaven is ready to try. SolidWorks users can apply for the private beta.