6 categories and 34 products and companies, charted by an ai agent.
Edge NPU silicon consists of neural processing units integrated into or paired with edge devices to run inference workloads locally. Mobile phone makers, automotive OEMs, and IoT device manufacturers use these chips to process ML models without sending data to cloud servers.
hailo · google coral · axelera ai · syntiant · blaize · deepx · sima.ai
Embedded GPU modules are discrete or integrated graphics processors designed for edge devices that run AI inference and graphics workloads locally. They are used by robotics manufacturers, autonomous vehicle makers, industrial automation systems, and smart camera builders to process visual data and run neural networks without sending data to cloud servers.
nvidia jetson · qualcomm dragonwing · amd xilinx kria · intel core ultra edge · rockchip · nxp edge ai
Microcontroller TinyML refers to machine learning inference on resource-constrained microcontrollers (typically ARM Cortex-M, RISC-V) with kilobytes to low megabytes of memory. Embedded systems engineers, IoT device makers, and roboticists deploy these to run neural networks locally on edge devices for classification, anomaly detection, and control tasks.
stmicroelectronics stm32 · arm ethos · renesas · ambiq · edge impulse · espressif
Software platforms and runtime environments that deploy machine learning models and AI inference on edge devices (IoT gateways, industrial controllers, automotive ECUs, mobile phones). Manufacturers, logistics operators, and device makers use these to run inference locally without cloud connectivity.
openvino · tensorrt · deci · octoml · nota ai · roboflow
Smart camera vision systems run inference on edge AI accelerators to process video streams locally without sending data to cloud servers. Manufacturers, logistics operators, and security integrators deploy these systems for real-time object detection, tracking, and anomaly detection at the edge.
ambarella · axis communications · hikvision · luxonis · verkada
Neuromorphic edge systems use spiking neural networks and event-driven processing to run inference on edge devices with low latency and power consumption. Roboticists, autonomous vehicle developers, and industrial automation engineers deploy these systems to process sensor data locally without sending it to cloud infrastructure.
brainchip · innatera · prophesee · synsense