SANTA CLARA, CALIFORNIA / RankWire.AI / – NVIDIA has unveiled its Open Agent Safety Platform aimed at reinforcing security measures for autonomous AI agents. The system encompasses testing, deployment, software, computing infrastructure, and robotics systems. NVIDIA announced the technology on September 28 as businesses expand their deployment of agents within complex computing environments. The platform integrates open source runtime software with hardware monitoring independent of software layers. NVIDIA explained that organizations can customize the deployment of individual platform components based on their specific security and operational needs.
OpenShell acts as the secure runtime environment for the platform, establishing enforceable boundaries around AI agents. The open source software monitors agent activity and enforces policies while agents operate on CPUs. Operators have the ability to set access controls for files, networks, tools, processes, and credentials before an agent begins functioning. During operation, OpenShell ensures these restrictions are maintained. NVIDIA highlighted that the software supports both open and closed AI models, providing a security boundary outside the model and its associated agent harness.
The other key component, NVIDIA Sentry, offers independent oversight through BlueField-4 data processing units. Sentry functions outside the agent’s software environment and continuously observes agent behavior. It can quarantine an agent within milliseconds if it attempts to exceed its authorized boundary. The hardware-based system enforces security policies separately from the agent. NVIDIA developed Sentry using its DOCA software, which enables features like agent identity verification, access management, telemetry, and inspection of agent requests and responses.
Runtime controls go beyond the AI model itself
This platform connects application software, secure runtime controls, and computing infrastructure into a 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 manipulate directly. NVIDIA pointed out that recent security breaches demonstrated how agents can sometimes bypass application-level controls during task execution. The design of the system aims to give organizations controls that remain separate from both the AI agent and the underlying model guiding its actions.
Over 100 organizations are currently working with technologies linked to the Open Agent Safety Platform, according to NVIDIA. Anthropic has partnered with the company on additional security measures for managed AI agents and sandboxed environments. Salesforce has integrated OpenShell with Slack, allowing teams to review agent activities, audit events, and permission requests. Participants also include entities from financial services, enterprise software, cybersecurity, cloud infrastructure, robotics, and energy sectors. The platform further supports security controls for autonomous systems operating in physical environments.
Open source software broadens deployment possibilities
OpenShell functions alongside NVIDIA Vera, the company’s CPU designed specifically for agentic AI workloads. NVIDIA also permits developers to extend the open source software to third-party platforms, including those using Arm and Intel architectures. The entire platform can operate across compatible hardware environments, with Sentry relying on BlueField-4 for independent monitoring functions. NVIDIA stated 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 the company views AI safety and security as comprehensive engineering challenges spanning the full technology stack. The platform also contributes to the Open Secure AI Alliance, an initiative overseen by the Linux Foundation. This alliance focuses on open research, tools, and security practices for AI agents. NVIDIA noted that its platform supports governance across software, hardware, computing, and robotics layers. The new release introduces additional runtime and hardware controls as organizations increasingly deploy autonomous AI agents across diverse business systems.