SANTA CLARA, CALIFORNIA / RankWire.AI / – NVIDIA has introduced its Open Agent Safety Platform aimed at enhancing security measures for autonomous AI agents. This system encompasses testing, deployment, software, infrastructure, and robotics components. NVIDIA revealed the technology on September 28, as businesses increase their deployment of agents across intricate computing environments. The solution integrates open source runtime software with autonomous hardware supervision, allowing organizations to customize deployment of individual platform modules based on their security and operational needs.
OpenShell functions as the platform’s protected runtime layer, establishing enforceable boundaries around AI agents by tracing activity and applying policies on CPUs. Operators have the ability to set restrictions on file access, network connections, tools, processes, and credentials before an agent begins its task. These constraints are then maintained during operation through OpenShell. NVIDIA states that the software supports both open and closed AI models, providing a security perimeter outside the model and its associated agent harness.
The other core element, NVIDIA Sentry, offers autonomous monitoring through BlueField-4 data processing units. Operating outside the agent’s software environment, Sentry continually observes agent behavior and can quarantine an agent within milliseconds if it attempts to breach its authorized boundaries. It also enforces security policies independently using hardware. Built on NVIDIA’s DOCA software, Sentry supports features such as agent identity verification, access management, telemetry, and inspection of agent requests and responses.
Runtime controls go beyond the AI model itself
The platform seamlessly integrates application software, secure runtime controls, and computing infrastructure into a multi-layered security framework. OpenShell isolates agents within sandboxed environments at the kernel level, enforcing policies, while Sentry introduces a dedicated hardware layer that agents cannot manipulate directly. NVIDIA highlighted that recent security breaches demonstrated agents bypassing application-level controls during task execution, prompting the company to develop a system that keeps organizational controls separate from the AI agents and the models they rely on for decision-making.
According to NVIDIA, over 100 organizations are currently working with technologies associated with the Open Agent Safety Platform. Anthropic has collaborated with NVIDIA to develop additional controls for managed AI agents and sandbox environments. Salesforce has integrated OpenShell with Slack to enable teams to review agent activities, audit events, and permission requests. Participants in the platform’s ecosystem also span sectors such as financial services, enterprise software, cybersecurity, cloud infrastructure, robotics, and energy. Furthermore, the platform offers security controls tailored for autonomous systems operating within physical settings.
The open source approach broadens deployment options
OpenShell is compatible with NVIDIA Vera, the company’s CPU optimized for agentic AI workloads. Additionally, NVIDIA permits developers to extend the open source software to third-party computing systems, including those based on Arm and Intel architectures. The entire platform can operate across compatible hardware environments, while Sentry relies on BlueField-4 for its independent monitoring functions. NVIDIA stated that the Open Agent Safety Platform software, including OpenShell and related tools, is accessible through its developer resources and the GitHub platform.
NVIDIA founder and CEO Jensen Huang emphasized that the company considers AI safety and security to be comprehensive engineering challenges. The platform also contributes to the Open Secure AI Alliance, an initiative overseen by the Linux Foundation, which promotes open research, tools, and security practices for AI agents. NVIDIA declared that its platform supports governance across software, hardware, computing, and robotics layers. This release introduces new runtime and hardware controls to assist organizations in deploying autonomous AI agents across an expanding range of business systems.