NXP unveils eIQ Agentic AI framework for secure edge autonomy
NXP Semiconductors has introduced a new eIQ Agentic AI Framework aimed at accelerating the deployment of autonomous, real-time AI directly on edge devices. The company positions the framework as a key building block in its long-term edge AI strategy, combining agentic AI software with its secure edge processing hardware portfolio.
For eeNews Europe readers working on industrial, automotive, healthcare or building automation systems, the announcement is particularly relevant as it addresses a growing need for low-latency, deterministic AI decision-making without reliance on cloud connectivity. It also highlights how agentic AI concepts are moving from research into deployable edge platforms.
Bringing agentic AI to the edge
According to NXP, the eIQ Agentic AI Framework is among the first solutions designed specifically to enable agentic AI development at the edge. It targets applications that require autonomous decision-making under strict real-time and safety constraints, such as factory automation, medical monitoring, robotics and smart infrastructure.
The framework is designed to remove development bottlenecks by supporting deterministic real-time decision-making and coordinated operation of multiple AI models. Edge-based agents built using the framework can, for example, stop factory equipment in response to safety risks, alert medical staff to urgent patient conditions, or autonomously adjust HVAC systems to mitigate hazards such as fire, all without cloud dependence.
“With the new agentic AI capabilities delivered by the eIQ Agentic AI Framework, NXP is bringing autonomy to edge AI devices and delivering a crucial building block for our long term edge AI vision. We’re empowering both novice and experienced developers with a secure, real time, hardware optimized software platform to quickly deploy similar AI-enabled functions to new use cases, improving time to market and reducing development overhead,” said Charles Dachs, Executive Vice President and General Manager, Secure Connected Edge at NXP Semiconductors.
Industry partners are already exploring the technology. “At GE HealthCare (see our news), supporting clinicians with tools that allow them to spend more time on patient care is a primary focus,” said Jeff Caron, Chief Digital and Technology Officer, Patient Care Solutions at GE HealthCare, pointing to concepts shown at CES that combine GE HealthCare technology with NXP’s eIQ AI Toolkit and the new framework.
Optimisation, security and developer flexibility
The eIQ Agentic AI Framework supports NXP’s i.MX 8 and i.MX 9 application processors as well as Ara discrete NPUs, allowing developers to scale agentic workflows across different hardware platforms. It aligns with emerging open agentic standards such as Agent-to-Agent (A2A) and Model Context Protocol (MCP), enabling easier integration and portability.
To meet real-time edge requirements, the framework includes hardware-aware model preparation, automated tuning and an intelligent scheduling engine that distributes workloads across CPU, NPU and other accelerators. This enables multiple models—vision, audio, time-series and control—to run concurrently while maintaining deterministic performance.
Security is a central design consideration. NXP says the framework will include protections against prompt injection, adversarial inputs and model spoofing, complemented by hardware-level security features such as secure boot, runtime isolation and a hardware root of trust.
Alongside the framework, NXP has also introduced the cloud-based eIQ AI Hub, giving developers access to the full eIQ tool suite for faster prototyping, performance tuning and deployment, either in the cloud or on-premise.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
