Framework Enables Autonomous Agentic Intelligence in Edge Apps
The eIQ Agentic AI Framework developed by NXP Semiconductors supports autonomous agentic intelligence at the edge, expanding the company's edge-computing platform. The framework provides real-time autonomous decision-making in use cases that require low latency, high reliability, and data privacy.
Giving developers the ability to rapidly prototype and deploy agentic AI designs for autonomous edge devices, the eIQ Agentic AI Framework is a trusted foundation to prototype and deploy optimized, secure, autonomous AI systems at the edge.
When combined with NXP’s secure edge AI hardware, the eIQ Agentic AI Framework delivers low-latency performance, built-in security, and system resilience. It's designed to eliminate development bottlenecks with deterministic real-time decision-making and multi-model coordination. As a result, edge-based AI agents can control systems when safety risks arise to mitigate hazards without relying on cloud connectivity.
With the eIQ Agentic AI Framework, developers are able to integrate sophisticated, multi-agent workflows into existing toolchains. And novice developers can quickly build functional edge native agentic systems without requiring deep technical experience. Moreover, it lets developers create cloud-scale models for deterministic, low-latency execution in edge applications.
The eIQ Agentic AI Framework supports the i.MX 8 and i.MX 9 application processor families and Ara Discrete Neural Processing Units for scalable agentic workflows. This allows developers to quickly convert a multi-step AI agent workflow into an on-device edge AI deployment. The framework aligns with open agentic standards, including A2A (Agent to Agent) and Model Context Protocol (MCP).
The Framework integrates hardware-aware model preparation and automated tuning workflows to run multiple models in parallel, including vision, audio, time series, and control, while maintaining deterministic performance in constrained environments. To enable perception, classification, and decision-making tasks to run concurrently, an intelligent scheduling engine distributes workloads across CPU, NPU, and integrated accelerators.
Designed with security in mind, NXP’s eIQ Agentic AI Framework will include features to prevent prompt injection attacks, adversarial inputs, model spoofing, and more. The platform leverages the security of NXP’s edge intelligence hardware, such as secure boot, runtime isolation zones, and a hardware root of trust.
NXP's new eIQ AI Hub is a cloud-based developer platform providing access to edge AI development tools, including deployment on cloud-connected hardware boards for real performance reporting. The full tool suite, including eIQ Time Series Studio, eIQ GenAI Flow, and eIQ Agentic AI Framework, as well as the enhanced modular eIQ AI Toolkit, can be accessed online via the eIQ AI Hub or downloaded for on-premises use.
Related links:
About the Author
Alix Paultre
Editor-at-Large, Microwaves & RF
Alix is Editor-at-Large for Microwaves & RF.
An Army veteran, Alix Paultre was a signals intelligence soldier on the East/West German border in the early ‘80s, and eventually wound up helping launch and run a publication on consumer electronics for the U.S. military stationed in Europe. Alix first began in this industry in 1998 at Electronic Products magazine, and since then has worked for a variety of publications, most recently as Editor-in-Chief of Power Systems Design.
Alix currently lives in Wiesbaden, Germany.