Latest
Anthropic Pairs Claude Agents With NVIDIA's OpenShell to Lock Down Credentials and Permissions
Anthropic worked with NVIDIA to add security layers to Claude's agent stack. Claude Managed Agents now holds credentials in a separate vault the agent never sees, while NVIDIA's open-source OpenShell blocks every agent action unless explicitly allowed. Together they let companies log, restrict and verify what deployed agents can reach.
What changes for operators — For a 10-200 person company running Claude agents against CRM, support tickets or finance systems, this closes a real gap: until now, giving an agent broad tool access meant trusting the model itself not to misuse credentials. With Managed Agents separating the agent loop from the sandbox and vaulting credentials, and OpenShell enforcing a default-deny policy on every file, network call and data access, an operations lead can start an agent on narrow permissions, review the audit log, and widen access only where the log shows it's needed — turning agent rollout from a one-time trust decision into an auditable, reversible control process.