NVIDIA NemoClaw secures sandboxed Artificial Intelligence agents

NemoClaw gives Artificial Intelligence agent deployments a managed path into NVIDIA OpenShell sandboxes. The stack focuses on routed inference, network controls, lifecycle management, and hardened defaults for OpenClaw and Hermes.

NVIDIA NemoClaw is an open source reference stack for running always-on Artificial Intelligence agents more safely inside NVIDIA OpenShell sandboxes. The project combines guided onboarding, a hardened blueprint, routed inference, network policy, and lifecycle management through a command-line interface. Supported agents include OpenClaw as the default option and Hermes, which can be selected by setting NEMOCLAW_AGENT=hermes before running the installer or by using the nemohermes alias after installation.

The stack is documented around its plugin structure, blueprint lifecycle, sandbox environment, host-side state, and protection layers. Its documentation covers prerequisites, inference options, network policies, customized policy changes, security best practices, sandbox hardening, command-line commands, and troubleshooting. NemoClaw is positioned as part of an ecosystem with OpenClaw and OpenShell, including guidance on when to use NemoClaw instead of OpenShell alone.

Security is central to the project. NemoClaw includes baseline network rules, an operator approval flow, egress control, and sandbox hardening measures such as container security controls, capability drops, and process limits. Current priorities include improving install and onboarding reliability across tested platforms, strengthening sandbox hardening, credential handling, and network-policy defaults, validating local and routed inference behavior for supported provider paths, and keeping documentation, troubleshooting guidance, and agent skills aligned with supported workflows.

NemoClaw is described as an alpha project, with maintainers reviewing issues, discussions, and pull requests on a best effort basis without guaranteed response timelines. Setup and usage questions are directed to GitHub Discussions or Discord, reproducible bugs to GitHub Issues, and broader feature proposals to GitHub Discussions before an issue is opened. Security vulnerabilities must be reported through private channels listed in SECURITY.md, including the NVIDIA Vulnerability Disclosure Program, encrypted email to [email protected], or GitHub private vulnerability reporting.

54

Impact Score

Devin Desktop turns Windsurf into an agent command center

Cognition has renamed Windsurf as Devin Desktop, positioning the IDE as a unified surface for managing coding agents. The product keeps the existing editor experience while adding multi-agent workflows, shared context, and cloud handoff features.

NVIDIA advances U.K. sovereign Artificial Intelligence push

NVIDIA is positioning the U.K.’s sovereign Artificial Intelligence effort as a shift from policy to deployment, with new compute plans, startup funding and enterprise projects. The push spans cloud infrastructure, life sciences, coding, inference and developer training.

World Cup ball tests and OpenAI super app plans

Wind-tunnel experiments suggest Adidas’s Trionda ball could trade distance for stability at the FIFA World Cup. OpenAI is also weighing a broader ChatGPT revamp as Artificial Intelligence infrastructure and policy fights widen.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.