Design and Implementation of an Open-Source IoT AI Agent Architecture for the AGI Era

随着大语言模型(LLM)及边缘计算技术的发展，AI智能体(AI Agent)正逐步成为物联网(IoT)系统中的核心调度与控制单元。文章设计并实现了一套以AI智能体为核心的人工智能物联网(AIoT)系统架构，融合传感器/执行模块、边缘终端、本地/云端LLM推理引擎、云计算中心与n8n自动化平台。系统采用模块化设计，支持MCP调度架构与OPC UA、MQTT等协议通信，具备低延迟、高可扩展性和良好的工程可移植性。并重点介绍了系统构成、核心模块设计，以智能家具为典型应用实例及部署实验，展示其在各种AIoT行业应用场景下的实用性和开放性。With the advancement of Large Language Models (LLMs) and edge computing technologies, Artificial Intelligence Agents (AI Agents) are gradually becoming the core scheduling and control units in Internet of Things (IoT) systems. This paper designs and implements an AIoT system architecture centered around AI agents, integrating sensor/actuator modules, edge terminals, local/cloud-based LLM inference engines, cloud computing centers, and the n8n automation platform. The system adopts a modular design, supports the MCP scheduling framework, and communicates via protocols such as OPC UA and MQTT, offering low latency, high scalability, and strong engineering portability. This paper focuses on the system structure and core module design, and demonstrates its practicality and openness through a typical use case in smart home applications and deployment experiments, showcasing its potential across various AIoT industry scenarios.