Over the past decade, there has been a growing interest in the development of intelligent neural interface systems-on-chip (SoCs) for a range of neurological disorders and emerging brain-machine interface (BMI) applications. The shift toward creating intelligent systems featuring on-implant signal processing, neural biomarker extraction, and AI has replaced prior efforts that primarily focused on raw neural signal acquisition and data compression for off-body processing [1]–[4]. Integrating complex functions into miniaturized neural devices presents significant opportunities for various applications, including therapeutic devices for central nervous system (CNS) disorders, peripheral nerve prostheses, spinal cord interfaces, and beyond. In this paper, we review the latest advancements in the development of CMOS-based integrated circuits (ICs) for three categories of intelligent neural prostheses, all featuring embedded signal processing on the implantable or wearable device. These categories include: 1) Neural interfaces for closed-loop symptom tracking and responsive stimulation; 2) Neural interfaces for emerging network-related conditions, such as psychiatric and memory disorders; and 3) Intelligent BMI SoCs for movement and communication recovery following paralysis. These developments mark the beginning of a dynamic field, and we anticipate the emergence of an even wider array of smart neural prostheses in the years ahead.