NVIDIA Unveils Open Agent Safety Platform to Secure Autonomous AI Agents
NVIDIA has announced the NVIDIA Open Agent Safety Platform, an open software platform and reference system design to strengthen AI security from agent testing to deployment. This effort aims to help organizations secure and govern AI agents as they take on more autonomous work.
The platform places agents inside a policy-governed runtime, while using NVIDIA DOCA on NVIDIA BlueField-4 to verify agent identity, enforce access policies for data, tools, APIs, and services, and provide attested telemetry to inspect agent behavior and detect deviations.
IBM is proud to support this effort, integrating IBM Agent Identity, currently in Public Preview, and HashiCorp Vault with NVIDIA OpenShell. This integration gives every agent a verified identity and only the access it needs.