Current ChipStart UK Companies (Cohort #3)
Managed by SiliconCatalyst.UK
Chipletti is a UK-based fabless semiconductor design company focused on advancing AI inference performance through innovative 3D memory solutions. We develop memory chiplets and licensable interconnect IP that enables cost-effective 3D stacking, allowing AI hardware companies to expand memory capacity without significantly increasing power consumption. Our technology targets the critical metric of performance per watt per mm², addressing memory bottlenecks in high-performance, energy-efficient AI systems.
From Defence to Datacenter, Ethicronics develops low-level software to secure data-in-use and data-at-rest — starting with hardware assurance for defence/critical infrastructures.
Our non-destructive, universally applicable solution, currently in development, delivers 100% assurance across chips and boards, guaranteeing hardware authenticity without sampling or destructive testing.
By reducing assurance costs and bringing nanometre-level integrity/authenticity certificates, Ethicronics helps primes and government buyers avoid multimillion-dollar breaches, critical failures and secure strategic advantage in high-stakes environments.
We develop unique bioelectronic chip-based devices to measure trace chemicals in water and other liquids. Our devices provide real-time, quantitative measurements of target chemical concentration for environmental, industrial and biomedical liquid diagnostics in a form-factor that can be integrated with any conventional electronic system. By using bioengineered micro-organisms coupled to novel silicon chips, we can develop sensitivity to a diverse range of natural and synthetic chemical targets, including those which cannot be detected currently by existing technology.
Kelvin Quantum is a fabless design house for development of semiconducting circuits and full electronic systems capable of operating within cryogenic environments alongside growing quantum technologies. Kelvin Quantum systems allow quantum technology providers to scale up their technologies and bring them to market.
Computer vision-mediated AI is revolutionising a wide range of industries but is constrained by the simplistic data acquired when conventional cameras capture light. Prospectral is building optical chips and computer vision software that allow for cameras which capture extra dimensions of data from light. This data enables previously “invisible” insights in industries like mining (on-site material analysis), manufacturing (contamination, defect detection) and autonomous systems for robotics or automotive (enhanced classification and detection of surroundings).
Quantopticon has developed a unique, patent-protected simulation platform, Quantillion, that fundamentally transforms the design workflow for quantum-photonic devices. By enabling engineers and researchers to validate device architectures virtually “right-first-time”, Quantillion dramatically reduces both the cost and development time traditionally associated with iterative hardware prototyping. This streamlined approach accelerates the broader digital transition within the quantum technology sector, facilitating the creation of integrable, scalable components suitable for a wide range of high-impact applications – from ultra-secure communication networks to next-generation position, navigation and timing systems.
AI's growth faces two key roadblocks: energy consumption and data availability, ultimately restricting AI deployment. At Rayd Technologies, we are revolutionising the way computation is performed with a brain-inspired photonic computing hardware and accompanying algorithms. Our system offers orders of magnitude improvements in throughput and energy consumption for machine vision, and trains with up to 10X less data, enabling advanced AI models to be rapidly deployed at the edge.
RX Watt provides a leading solution for long-range RF wireless power transfer, combined with communication and RF sensing capabilities. This enables battery-free sensing in harsh industrial environments and low-cost, sustainable tags for logistics and supply chain. This is enabled by a scalable CMOS solution for high-sensitivity power reception and low-power communication.
SiDesign Works is an Oxford-based semiconductor startup creating the chips that power the future of satellite communications. Our designs enable smarter, more efficient antennas that connect people and systems anywhere on Earth and in space. We make connectivity faster, more reliable, and ready for the next generation of networks.
As a spin-out from the University of Southampton, Smith Optical is commercializing a breakthrough AR display technology called Wavemixing. Our patented approach delivers the industry's first 100% transparent, daylight-bright displays with true 3D depth and zero eye-glow. We are building the foundational display component that will enable the mass adoption of AR smart glasses.
Xen Quantum is building technology to make quantum communications more practical.
ChipStart UK Alumni (Cohort #2)
Apitronix Tasklet Processors™ are a new class of microprocessor developed specifically for embedded workloads. As computation has evolved to multicore architectures and software to move forward, this approach has proved challenging for the particular needs of embedded software. Apitronix is developing a novel chip, bus and toolchain that harnesses the power of many tiny cores, allowing them to work together cooperatively. This makes it easy to develop complex embedded software applications, reducing bugs, speeding time to market and introducing new supply chain flexibility.
At Heronic Technologies, we deliver state-of-the-art bespoke accelerator architectures for AI. Inspired by the great mathematician Heron of Alexandria, who pioneered the concept of automata in mechanics, we are redefining the automation of hardware design. We have produced the best-in-class hardware when it comes to TinyML, object detection and human action recognition tasks, setting the industry standard for performance and innovation. Our technology is compatible with the latest FPGA devices from leading vendors, including AMD, Altera, Lattice, Microchip, and GOWIN. Additionally, we are actively developing our ASIC toolflow to further expand our capabilities.
Our Aquarius TCAD tool is a new, user-friendly, affordable solution specifically designed for Wide Bandgap (WBG) technologies. It has been developed with the needs of users in mind, making advanced semiconductor design more accessible and efficient. Aquarius is tailored specifically for Wide Bandgap (WBG) semiconductors, while still supporting Silicon-based devices. This advanced tool incorporates dedicated models and numerical techniques to address the unique properties of WBG materials, ensuring accurate simulation of critical factors such as breakdown characteristics and reliability modelling.
Metahelios prides itself on providing completely new imaging technologies for several industries through a nanotechnological approach. We enhance imaging capabilities by using ultra-thin nanostructured materials, namely metasurfaces.
Metahelios was founded by two metasurface physicists in 2022, in Glasgow UK. Dr. Charles Altuzarra (CEO) and Dr. Yash D. Shah (CTO) are also experts of Biophotonics, Quantum Optics, and Terahertz.
Nanomation is a semiconductor software company that enables industry to unlock the transformative power of nanomaterials.
Our mission is to make faster, more powerful, and more efficient chips a reality through our world-first nanomaterial software.
Infrared spectroscopy in the palm of your hand, enabling material analytics insights everywhere, anytime to everyone.
You will probably say that vision is your most important sense…
…even though you can only see a minor part of the available information.
What if materials, substances and physiological markers could be identified at the point of need by everyone – simply by looking at them?
Unlimited applications in fields such as healthcare, waste sorting, personal care, material analytics, skincare, agriculture, robotics and security arise…
POM's medical-grade hormone monitor makes precise and personalised healthcare interventions easier based on selected biomarkers.
We believe the future is photonic. Our mission is to power it with clever electronics.
Our team of dedicated engineers, physicists, designers, and support staff build the things you need to power your photonic devices, get them to you when you need them, make sure things work, and support you if they don’t.
We are passionate about sustainability. We work hard to reduce our environmental footprint, whether by minimising power consumption, reducing packaging waste, or by focussing on lifecycle. We design and assemble at our Bristol HQ, and manufacture sustainably and equitably as nearby as possible.
Current Silicon Catalyst Accelerator Companies based in the UK
Accelerating & protecting compute-intensive applications
VyperCore is a fabless RISC-V processor startup
Applicable to all general-purpose programming languages, including C/C++
VyperCore's modified RISC-V processor will incorporate our novel hardware memory allocation management technology. This fundamental remodelling of hardware memory interfaces enables us to accelerate modern managed-language software, such as Python and C#, by up to a factor of 10. We can even achieve a >1.5x speedup on software written in older languages like C and C++.
Initially we are focusing on application software (as opposed to low-level system software) where we can maintain source code compatibility across languages (from Python to C/C++.) This will enable deployment of our accelerator card in data centers without developers needing to change their programs. Tweaked versions of popular open-source compilers and runtimes will be made available for early customers to retarget their applications. This is made much easier for us as the RISC-V community is already well underway porting tools to the architecture.
Introducing Ultra Edge® circuit-level artificial intelligence. Transforming the smart technologies and processes driving our world.
Ultra Edge® technology, redefines a new era of circuit design, enabling predictive maintenance and improved performance of every closed-loop control system.
'wee'
[wee]
adjective [Scottish] we·er, we·est.
little, very small, tiny
weeteq is an innovative Scottish company developing tiny technology that revolutionises Global industries. Our executive team have collectively spent over 50 years in deep tech and smart technology businesses, working for some of the world’s most respected tech companies.
We partner with other smart technology manufacturers and operators to deliver our mission of developing circuit-level artificial intelligence solutions to accelerate the sustainable growth of the smart technologies and processes driving our world.
Quantum Power Transformation (QPT) is a revolutionary start-up with a vision to help the world save energy through the development of unique IP that can revolutionise power electronics systems, radically improving efficiency & performance.
These benefit almost any consumer or industrial based electronic system; reducing power consumption, increasing efficiency and the reliability of power systems. Applications include ac:dc converters, dc:dc converters, inverters and electric motor control systems.
ChipStart UK Alumni (Cohort #1)
We develop light-speed photonic processors and network switches that enable faster, more sustainable computing.
Using photons for computation leverages their high speed and high bandwidth to deliver faster data transfer rates and capacity vs. electronic processors and electro-optical switches.
In addition to being faster, photons require less energy than electrons. Finchetto’s photonic processor and network switch deliver faster throughput for significantly less energy.
By taking a radically different approach, Finchetto’s processor can compute natively in any numerical base. This enables the encoding of more and/ or specific information delivering faster data transfer rates.
We have designed the fastest, most sensitive Single Photon Avalanche Detectors (SPADs) in the world that can operate at ambient temperature and be manufactured in a standard CMOS process.
We are having an immediate impact on the sensors used in Raman Spectroscopy, Fluorescence Imaging and Flow Cytometry, and are working hard to unlock huge opportunities in handheld and wearable personal healthcare, high throughput screening of genomics and proteomics and biomedical applications at the GP surgery and pharmacy.
Fast, efficient, and explainable AI using Tsetlin machines and logic approaches
Literal Labs has developed an ML technique that uses a combination of propositional logic and Tsetlin Machines to create fast, efficient, and explainable AI.
We all have a sense that AI has the potential to change the world for the better; to push humanity forward. To fulfil its potential, artificial intelligence must run at the edge wherever it is needed, and not be dependent on cloud connectivity. To meet society's needs, AI has to be explainable, it has to be fast, and it has to be economically and energy efficient. Literal Labs is working to make that happen.
Through years of collaborative research between Newcastle University (UK) and the Center for AI Research at University of Agder (Norway), an approach to machine learning emerged that uses a combination of data binarisation, propositional logic, and Tsetlin Machines. It's that technological combination upon which we were founded. Spun out from Newcastle University in 2023, Literal Labs is on a mission to create fast, efficient, and explainable AI perfect for edge use.
SECQAI’s (se-kai’s) Q-Locked solution secures computation and communication which are the two domains with the largest threats.
Our solution solves both the running of secure applications that aren't liable to memory injection attacks and integrating communication between devices with a communication standard that is secure against quantum computing and won't break when deployed.
Vaire Computing is addressing the problem of scaling computing power beyond the thermal limits that threaten the end of Moore's law by developing near-zero energy chips based on a reversible computing architecture.
We are tackling the problem of low yield in compound semiconductor fabrications with our ground-breaking hyperspectral imaging technology combines high throughput and accuracy, delivering 100% wafer inspection in minutes.
Blueshift Memory’s proprietary chip design optimizes the memory architecture for more efficient handling of large data sets and time-critical data, enabling up to 1,000 times faster memory access for specific data-focused applications. These include high performance computing, artificial intelligence (AI), machine vision for augmented and virtual reality (AR/VR), 5G edge connectivity and the Internet of Things (IoT). The focus of Blueshift Memory’s technology is the Cambridge Architecture™, the next-generation technology for stored-program machines, designed to replace the currently-used modified Harvard architecture and to overcome the traditional constraints of the von Neumann bottleneck.
RED has invented the VISC processor (Vector+RISC), achieving massive execution efficiency for Edge AI and other applications.
It enables advanced security software, answering the no.1 pain point for Edge AI.
It delivers up to 100X the efficiency of today’s solutions, answering the no.2 pain point: performance requirements.
Its low bandwidth architecture makes it inherently low-power: the no.3 pain point.
Smart design means it’s no harder to get applications running on VISC than a traditional RISC processor. Binaries are smaller, and we work with standard compilers.
Integrated photonics uses the same scalable process used to make semiconductor electronics chips to make circuits for light. It’s being used as the platform for energy-efficient communications, wearable healthcare sensors, rapid diagnostic tools, optical tensor processors, on-chip lidar, quantum computing and communication, and a host of other transformative technologies.
Wave Photonics is using computational techniques to create tools and IP to enable and accelerate the development, mass production and adoption of these technologies. We believe that many obstacles integrated photonics technologies face can be removed using a combination of simulation, statistical modelling and optimisation techniques, so we’re creating and testing a new way to approach photonics design.
We’re located in Cambridge, UK, and are backed by great investors in Silicon Valley including Plug and Play Ventures, as well as Cambridge Enterprise and a range of US and European angel investors. We’re also leading multiple projects funded by Innovate UK, the UK's innovation agency, to apply our approach to advancing quantum technologies.
If you want to find out more, or if you’re as excited as we are about the world-changing technologies that will be enabled by integrated photonics and want to play a part in it, then please get in touch via our website.
We are pioneering the use of semiconductor technology for next-generation neural implants.
Our mission is to provide the best possible outcomes for patients with neurological conditions by delivering the highest performance with the least invasive surgery.a
Our team brings together world-class experts in neuroscience, microtechnology, and implantable neural interfaces — augmented with medtech industry pedigree and clinical experience.
We are addressing the Power-Performance issues of petabyte-scale data processing problems by unifying compute and memory with a 100% enterprise software compatible low-energy processor in memory.
Silicon Catalyst Accelerator Alumni based in the UK
Salience Labs is building a hybrid photonic-electronic chip for AI. We have designed a massively parallel, ultra-high throughput Photonic Tensor Processing Unit. Photonics allows data to be modulated at up to 100 GHZ, and allows for high levels of parallelization using multiplexing. We integrate this photonic unit into a SoC architecture designed to exploit its high throughput for AI inference. Salience Labs technology is based on decades of research collaboration between Oxford University and University of Münster, Germany.