Edge AI integrates AI with edge computing to process data closer to the source, enhancing real-time performance and data security. This review explores Edge AI's development, challenges, and future directions. It presents a taxonomy to classify Edge AI systems and examines their applications across various domains, including smart cities, manufacturing, autonomous vehicles, industrial automation, and healthcare. The study highlights the importance of Edge AI in real-time data processing, while addressing challenges such as resource constraints, security threats, and scalability. It also proposes future research directions to overcome these limitations. The review methodology includes a systematic analysis of existing literature, identifying key trends and gaps in Edge AI research. The taxonomy covers infrastructure, cloud computing, fog computing, services, machine learning, and resource management. The study emphasizes the role of AI in optimizing Edge AI systems, improving efficiency, and enabling real-time decision-making. It also discusses the integration of AI with edge technologies, highlighting benefits such as reduced latency, energy efficiency, and enhanced security. The review concludes that Edge AI is a critical technology for future applications requiring low-latency, high-security, and real-time data processing.Edge AI integrates AI with edge computing to process data closer to the source, enhancing real-time performance and data security. This review explores Edge AI's development, challenges, and future directions. It presents a taxonomy to classify Edge AI systems and examines their applications across various domains, including smart cities, manufacturing, autonomous vehicles, industrial automation, and healthcare. The study highlights the importance of Edge AI in real-time data processing, while addressing challenges such as resource constraints, security threats, and scalability. It also proposes future research directions to overcome these limitations. The review methodology includes a systematic analysis of existing literature, identifying key trends and gaps in Edge AI research. The taxonomy covers infrastructure, cloud computing, fog computing, services, machine learning, and resource management. The study emphasizes the role of AI in optimizing Edge AI systems, improving efficiency, and enabling real-time decision-making. It also discusses the integration of AI with edge technologies, highlighting benefits such as reduced latency, energy efficiency, and enhanced security. The review concludes that Edge AI is a critical technology for future applications requiring low-latency, high-security, and real-time data processing.