AnalogAI Chooses SST’s memBrain SAGE IP for Edge AI Processors

CHANDLER, Ariz., Sept. 15, 2026 /CourierPR/ -- AnalogAI, a company based in the Seoul area of South Korea, has selected memBrain™ SAGE neuromorphic hardware intellectual property (IP) from Microchip Technology’s Silicon Storage Technology® (SST®) subsidiary for its first real-world edge AI processors. This move aims to enhance the company's ability to deliver high levels of analog compute-in-memory (aCIM) performance while maintaining ultra-low power consumption.

AnalogAI's processors are designed to simultaneously train and run inference on AI models in real-world environments, enabling edge devices to adapt to sudden changes in their physical surroundings. Mark Reiten, senior vice president of Microchip’s Intelligent Compute business unit, highlighted the significance of this partnership.

The memBrain SAGE IP, developed by SST, features a range of advanced technologies, including the memBrain Tensor In-Memory Logic Element (TILE), optimized ESF3 bitcell, custom array, decoders, and driver circuitry, as well as optimized DACs and ADCs. The memBrain SAGE IP also includes summator and high voltage bias circuitry, nanoamp level bitcell control logic, and proprietary test circuitry. These components work together to provide reliable, high-performance, and low-power non-volatile storage directly on the chip, making it ideal for applications that require fast access times, high endurance, and data retention without the need for external memory components.

Jaejun Lee, AnalogAI’s chief executive officer, emphasized the company's commitment to pioneering new functionality for edge AI devices.

The memBrain SAGE IP has been developed and deployed in 40 nm and 28 nm foundry processes using production-ready SuperFlash memory. The current technology roadmap includes 22 nm memBrain SAGE IP development. Designed to provide reliable, high-performance, and low-power non-volatile storage directly on the chip, SuperFlash memory is widely used in applications that require fast access times, high endurance, and data retention without the need for external memory components.

By leveraging the robust silicon-proven SST memBrain SAGE IP, AnalogAI aims to deliver high-performance, low-power edge AI processors that can adapt to real-world environments in real-time. This partnership underscores the growing importance of edge computing in today's rapidly evolving technological landscape, where devices must be able to process and respond to data quickly and efficiently, even in the absence of a central server.