The rapid expansion of edge computing and Internet of Things (IoT) ecosystems has introduced new cybersecurity challenges, particularly in decentralized, resource-constrained environments where traditional security models often fall short. This paper proposes an immune-inspired artificial intelligence framework (I3AI) that draws on core principles of biological immune systems including self-organization, local learning, and immune memory to enable adaptive, privacy-preserving defense mechanisms across distributed edge nodes. The architecture incorporates federated learning to maintain a decentralized threat intelligence network while ensuring data privacy and minimal communication overhead. I3AI was evaluated through large-scale simulations involving 10,000 virtual devices and tested in real-world deployments across varied geographic locations. Results demonstrated a 42% improvement in detection accuracy and a 53% reduction in false positives compared to baseline methods. Additionally, the framework achieved a 38% reduction in energy consumption for security operations. Notably, I3AI successfully identified 72% of simulated zero-day attacks within 24 hours, showcasing its adaptability to evolving threats. These outcomes underscore the potential of biologically-inspired AI to deliver scalable, efficient, and resilient cybersecurity for emerging edge environments, addressing key limitations of conventional centralized approaches.