Add Runtime Controls to AI Agents with NVIDIA OpenShell
NVIDIA OpenShell is an open source runtime that controls which systems and data an AI agent can access.
The runtime combines sandboxed execution, controlled service access, credential management, and formal policy analysis to restrict API operations and protect credentials outside the agent workload.
Organizations including Cadence, Slack, and Gecko Robotics are adopting OpenShell for chip design, enterprise automation, and physical robotics governance.
Watch next
Watch OpenShell 0.1.0 release notes for sandbox policy changes and deployment examples.
NVIDIA OpenShell (Apache 2.0) is an open source secure runtime for executing autonomous AI agents in sandboxed environments with kernel-level isolation