🚀 A First in the Industry from Advantech: Edge AI Agent System with Built-in 4x 10GbE Support!

[Hasan S. Cemkan]

🌟 Designed for Next-Gen AI: AIR-075​

Advantech has announced its AIR-075 Edge AI Agent System, specifically designed for next-generation vision processing and agent-based AI applications. Powered by NVIDIA Jetson Thor, this system delivers a massive 2,070 TFLOPS of AI processing power and features four built-in 10GbE ports optimized for high-bandwidth, multi-camera setups.

⚡ High Bandwidth and Multi-Camera Support​

The AIR-075 leverages NVIDIA Jetson Thor with NVIDIA Blackwell architecture to deliver high-performance AI inference in a compact, thermally optimized, industrial-grade chassis. Its four built-in 10GbE RJ45 interfaces provide the immense bandwidth required for multiple IP cameras, enabling real-time video ingestion and AI processing without the need for external network switches. This direct connectivity reduces system complexity and integrates seamlessly with existing IP-based factory vision infrastructures. With a wide 19–36V DC power input and flexible M.2 expansion options for NVMe storage, 5G, and Wi-Fi, the AIR-075 offers a highly scalable foundation for autonomous machines and distributed edge AI deployments.

🤖 Rapid Agent-Based AI Deployment​

The AIR-075 is supported by Advantech's edge AI software ecosystem, NVIDIA's open models (NVIDIA Cosmos, NVIDIA Nemotron, NVIDIA GR00T), and NVIDIA JetPack 7.2, simplifying development, deployment, and fleet operations. Advantech WEDA serves as the AI deployment infrastructure for the AIR-075, providing centralized lifecycle management for AI models, agent workflows, software updates, and operational policies in distributed edge environments. Combined with NVIDIA NemoClaw-compatible runtime support, the AIR-075 enables multimodal AI agents to interact with cameras, sensors, enterprise systems, and physical devices through natural language and automated workflows. The Advantech Edge AI SDK offers pre-validated AI frameworks, development tools, and reference models, while NVIDIA JetPack 7.2 brings agent-friendly Jetson software and official Yocto support for custom Linux distributions, optimizing system performance.

💡 Fast Transition from Concept to Production​

By combining NVIDIA Jetson Thor's AI processing power with Advantech's deployment-ready hardware and software ecosystem, the AIR-075 significantly reduces the effort required to transition from concept to large-scale production for physical AI in industrial environments.