SANTA CLARA, CALIFORNIA / RankWire.AI / – NVIDIA has introduced its Open Agent Safety Platform to bolster security measures for autonomous AI agents on a global scale. This platform encompasses testing, deployment, software, computing infrastructure, and robotics systems. NVIDIA revealed the technology on September 28 as businesses expand their utilization of agents within complex computing environments. It combines open source runtime software with independent hardware monitoring to enhance security. NVIDIA noted that organizations can customize the deployment of individual platform components based on their specific security and operational needs.
OpenShell functions as the platform’s secure runtime layer, establishing enforceable boundaries around AI agents. This open source software tracks agent activity and enforces policies while agents operate on CPUs. Operators can set permissions for file access, networks, tools, processes, and credentials before the agent begins its task. During operation, OpenShell ensures these limits are maintained. NVIDIA stated that the software supports both open and closed AI models and provides a security boundary outside the model and its agent harness.
The other major element, NVIDIA Sentry, offers independent monitoring via BlueField-4 data processing units. Sentry operates outside the agent’s software environment, continuously overseeing agent behavior. It can quarantine an agent within milliseconds if it attempts to exceed its permitted boundaries. This hardware-based enforcement independently maintains security policies. Built on NVIDIA’s DOCA software, Sentry supports agent identity verification, access controls, telemetry, and inspection of requests and responses.
Runtime controls extend beyond the model
The platform integrates application software, secure runtime controls, and computing infrastructure into a multi-layered security architecture. OpenShell isolates agents within sandboxed environments with kernel-level separation and policy enforcement. Sentry adds an independent hardware layer that agents cannot directly manipulate. NVIDIA highlighted recent security incidents where agents bypassed application-level controls during task execution. The system was designed to provide organizations with controls that remain separate from both the AI agent and the controlling model.
Over 100 organizations are actively using technologies linked to the Open Agent Safety Platform. Anthropic has partnered with NVIDIA on additional controls for managed AI agents and sandbox environments. Salesforce has integrated OpenShell with Slack, enabling teams to review agent activities, audit events, and permission requests. Participants also include firms from financial services, enterprise software, cybersecurity, cloud infrastructure, robotics, and energy sectors. The platform further supports security measures for autonomous systems operating in physical environments.
Open source software broadens deployment capabilities
OpenShell works alongside NVIDIA Vera, the company’s CPU designed for AI workloads involving agents. NVIDIA also permits developers to extend the open source software to third-party platforms, including systems utilizing Arm and Intel technology. The entire platform can operate across compatible hardware environments, with Sentry leveraging BlueField-4 for independent monitoring. NVIDIA clarified that the Open Agent Safety Platform software, including OpenShell and related features, is accessible through its developer resources and the GitHub platform.
NVIDIA founder and CEO Jensen Huang emphasized that AI safety and security are full-stack engineering challenges. The platform also contributes to the Open Secure AI Alliance, an initiative overseen by the Linux Foundation. This alliance promotes open research, tools, and security practices for AI agents. NVIDIA confirmed that its platform supports governance across software, hardware, computing, and robotics layers. The release introduces new runtime and hardware controls to support organizations deploying autonomous AI agents across an expanding array of business systems.