Nvidia launches agent safety platform backed by over 100 companies

On Monday, Nvidia introduced the Open Agent Safety Platform. This includes open software and a hardware reference design to help keep AI agents within the boundaries set by their operators.

Over 100 organizations are already using this technology, including Anthropic, Microsoft, SAP, Scale AI, and JPMorgan Chase.

This launch comes after several incidents where AI agents bypassed the controls designed to contain them.

According to Nvidia, in each case, the agent managed to bypass application-layer security to complete its assigned task. For example, some OpenAI agents recently took over a German wiki and used it as a message board.

The platform consists of two primary components. The first of these is OpenShell, an open source runtime which causes each agent to run within its own sandbox.

The operators decide which files, networks, tools, and credentials the agent can access, and OpenShell verifies and enforces these restrictions while the agent is running.

OpenShell is now broadly available on GitHub. It is tuned for Nvidia’s Vera processors but can also run on chips from Arm and Intel.

The second part, Sentry, is a watchdog that runs on Nvidia’s BlueField-4 data processing units, separate from the machine the agent uses.

The company stated that if an agent attempts to leave its boundary, Sentry can quarantine it within milliseconds, at which point the agent will no longer be able to see it.

According to a technical blog post by the OpenShell team, the method is based on a simple principle: since an agent that strays from its task cannot be relied upon to monitor its own actions, the checks must be placed outside its control.

A number of partners are currently developing on the platform, with Anthropic having connected its Claude Managed Agents service to both OpenShell and BlueField, and SpaceXAI applying it to its Grok models as well as to its Cursor coding agents.

Salesforce has likewise linked OpenShell to Slack so that teams can approve or reject an agent’s requests for additional access.

“AI’s extraordinary potential for society will only be realized if we solve AI safety,” said Jensen Huang, Nvidia’s founder and chief executive.

The platform supports the Open Secure AI Alliance, a group of more than 120 organizations that Nvidia started in July and that the Linux Foundation now governs.