The machine stops needing the network
Perception and decision both complete on the device. A product works the same in a tunnel, in a basement, at sea and in a factory that will not put its line on the public internet.
Neuromorphic computing
Intelligence built for the real world
Neuromorphic computing brings memory and computation together, taking inspiration from the way biological systems process information. CyberSwarm is building this architecture in hardware, using devices that compute inside their own memory to deliver fast, efficient intelligence at milliwatt power—ready for sensing, perception and decision-making beyond the data centre.
The bottleneck
Today’s computers spend more energy moving information than processing it.
Conventional processors separate memory from computation, forcing AI models to move data continuously between the two. That cost can be absorbed in a data centre, but not in machines constrained by power, heat and response time. CyberSwarm’s neuromorphic hardware stores and processes information in the same physical devices, enabling fast, local intelligence within milliwatt power budgets.
- Draper Associates
- Backed since 2017
- 2017
- Building since
Early institutional backing
Nine years of device work
What changes
Four capabilities unlocked by neuromorphic computing
The engineering behind each one is on the technology page.
The power budget stops being the ceiling
Computation happens where the data already sits, so the energy that used to go into moving numbers is simply not spent. That is the difference between a feature that fits in a battery-powered product and one that does not.
The response arrives inside the control loop
A decision reaches the actuator in microseconds rather than after a round trip. For anything that steers, brakes, grips or corrects, that is not a nicety. It is the whole requirement.
The data never leaves the product
A camera that recognises a driver without sending the driver anywhere changes what is legally and commercially possible. Privacy stops being a policy and becomes a property of the hardware.
See it work
The calculation is the current
This is the engine, live. Hover a sensor channel to feed it a signal, then activate it to send the whole input through at once and watch the answer appear along the bottom. What takes a conventional processor millions of operations happens here in a single pulse, because the components are doing the arithmetic themselves.
- The model is held in the hardware itself, not loaded into it
- Running it costs a pulse of current rather than millions of trips to memory
- The whole calculation resolves at once, in the time it takes the current to settle
- Nothing is fetched, nothing is written back, and nothing is sent anywhere
Why us
Four advantages that require a different architecture
A different machine, not a faster one
Everyone else is making the existing architecture more efficient. We removed the part that costs the energy: the memory and the arithmetic are the same physical component. That is not a tuning gain, and it is not something a competitor reaches by iterating.
Owned down to the material
The portfolio starts at how a resistive state is written into a thin film and runs up to the full network. Anyone building this way meets our filings at the device layer, which is the layer that is hardest to design around.
Sold as an engine, not as a chip
Partners license the architecture into their own silicon or take it as a module. That fits how automotive, aerospace and medical companies already buy, and it means one design win can carry a platform rather than a product.
Built for things that must not stop
Work is spread across many small arrays, so damage costs precision in one region instead of taking the system down. In the sectors we sell into, that behaviour is a requirement before it is an advantage.
Where it goes
Six industries where the answer has to arrive on the device
From a driver-monitoring camera to an orbital imaging payload, the same constraint keeps reappearing: fixed power, no network, hard deadline.
Automotive
Perception that keeps working when the link does not
Sensor fusion, driver monitoring and predictive diagnostics that run inside the ECU on a power budget a vehicle can actually spare, with a wake-up that costs nothing, because the weights never left the array.
Aerospace & Defence
Autonomy for platforms that are on their own
On-board processing for airborne and orbital systems where the downlink is narrow, contested or absent, and where a single-event upset must degrade the answer, not end the mission.
Robotics & Physical AI
A control loop that closes in the robot
Reflex-rate perception and control for manipulators, mobile robots and drones, where a decision that arrives 200 ms late is not a decision at all.
Healthcare & Medical Devices
Continuous monitoring that never uploads a patient
Wearable and implantable devices that classify physiological signals on the device, where privacy is a property of the architecture rather than a clause in a policy document.
Industrial & Energy
Condition monitoring on machines that were never networked
Retrofit intelligence for factory floors, grid assets and remote infrastructure. Nodes that run for years on a harvested or battery supply and report an event, not a stream.
Consumer & IoT
Always-on intelligence inside the device
Wake-word, presence, gesture and context awareness that stay on continuously without the power draw or the privacy cost. Because the array is transparent, it can sit behind the display.
For partners
Put the engine in your product
Evaluation and integration start the same way: one workload, one power envelope, one deadline, and a conversation with the engineers who built the engine.
For investors
Why this architecture, and why now
Nine years of device work, backing from Draper Associates, and the market thesis behind the architecture.
Newsroom
Latest
25 March 2025From CyberSwarm
Our journey to revolutionise AI
Seventy five years after Turing asked whether machines can think, the answer is being limited by the machine underneath.
13 March 2025From CyberSwarm
The future of artificial intelligence is neuromorphic computing
Neural networks need processing power and energy that conventional hardware cannot keep supplying.
14 February 2025From CyberSwarm
Building the artificial ant
Every living thing is built on a pattern. What happens when you build a processor on the same one.
Real-world intelligence needs a different kind of compute.
Whether you are evaluating the architecture for a product or the company for a portfolio, the conversation starts the same way.