OpenShell v0.0.43 🛠️ bidirectional TTY streaming 🔒 OIDC auth in the TUI 🧩 HTTPS and mTLS decoupled 📦 TOML gateway config (RFC 0003) 🖥️ sandboxes boot from ext4 disks 🛡️ DNS removed from sandbox mapper to block exfiltration Authentication, streaming, and sandbox isolation improvements.

OpenShell v0.0.41 🧩 agent-driven policy management 🎚️ sandbox resource flags in the CLI 🔒 custom CA support for OIDC TLS verification 📥 sandbox downloads with workspace-boundary checks 🔧 bug fixes and stability improvements Policy and resource control, directly from the shell.

OpenShell v0.0.40 🔀 local-domain service routing in the gateway ☸️ k8s node scheduling + tolerations 🔒 CLI TLS now uses the OS trust store 🛡️ SecretResolver debug no longer leaks secrets Two security fixes ship alongside new routing and K8s scheduling control.

OpenShell v0.0.37 🧩 pluggable compute drivers: Docker, Podman, Kubernetes, MicroVM 🔒 OIDC + RBAC gateway auth ☸️ Helm chart + Kubernetes user namespaces 📦 Debian, RPM, and Homebrew packages breaking: recreate the gateway before upgrading.

NVIDIA's OpenShell uses the Z3 theorem prover to verify agent actions. When denying a path, it returns the exact constraint adjustment needed. Binary guardrails just halt the loop. Returning structured counterexamples turns a block into a solvable recovery step.

Building on our earlier introduction to @nvidia #OpenShell# and our role as an official inference provider, today we’d examine how it powers safer, production-ready autonomous #agents#. In our latest blog, we’ll explore: 🔹What NVIDIA OpenShell is and why it matters for long-running, autonomous agents 🔹How its architecture enables safer and more controlled agent execution 🔹Real-world use cases and deployment approaches for agent systems As AI moves beyond experimentation toward persistent, agent-driven systems, the focus is shifting from models to how these systems are executed, governed, and scaled. Read the full blog to learn more 🔗: #AgenticAI# #AIAgents# #neocloud#

$NVDA LAUNCHES OPEN AGENT SAFETY PLATFORM Nvidia is introducing OpenShell software and the Sentry reference system design to let companies set enforceable limits on what AI agents can access and do, with security controls operating outside the agents themselves. OpenShell, the open-source software layer, controls access to files, tools and external services, protects credentials and records permission decisions. It works with existing agents such as Claude Code, Codex and Hermes without requiring developers to rewrite them. Sentry adds a separate hardware watchdog running on Nvidia’s BlueField-4 processors. Nvidia says it continuously monitors agent activity from outside the agent’s environment and can quarantine agents attempting to cross their boundaries within milliseconds. The approach is designed for agents that work for hours or days, write code and interact with business systems. Instead of relying only on the model to follow instructions, the infrastructure limits which actions it can actually carry out. Anthropic has collaborated with Nvidia to add protections to Claude Managed Agents, while SpaceXAI is using the platform for Cursor coding agents and Grok models. Salesforce has integrated OpenShell with Slack, and SAP is embedding it into Joule Studio. Nvidia says more than 100 organizations are working with the technologies, including Microsoft, CrowdStrike, Cisco, Palo Alto Networks, Palantir and ServiceNow. The effort also extends to robotics, banks and energy infrastructure. Jensen Huang: “Safety and security require full-stack engineering.” OpenShell is broadly available, with platform software accessible through Nvidia’s developer resources and GitHub. Sentry is presented as a BlueField-4-based reference system design.

We are excited to share that Bitdeer AI Cloud is now supporting @nvidia #OpenShell#, an open source runtime designed to safely build and deploy autonomous, self-evolving agents 🤖. Powered by high-performance NVIDIA GB200 NVL72 systems in our AI DC, Bitdeer AI Cloud provides the infrastructure required to run long-running agent workloads at scale. Developers can build your own AI agent on NVIDIA OpenShell, and seamlessly deploy them on Bitdeer AI Cloud, enabling secure execution, sandboxed environments, and reliable compute for persistent agent systems. This collaboration aligns closely with key themes from the NVIDIA GTC 2026 keynote, where Jensen Huang highlighted the shift toward agentic AI, AI factories, and infrastructure designed to support reasoning, inference, and execution at scale. As AI systems move from simple inference toward autonomous workflows, secure agent runtimes combined with high-performance infrastructure will become a critical foundation for the next generation of AI applications. We’ve compiled more key highlights from the keynote. Read the full summary on our blog🔗： #neocloud# #NVIDIA# #NemoClaw# #Inference# #GTC26#

Nvidia $NVDA just announced NVIDIA Open Agent Safety Platform to try and fix the safety and governance problem with Agentic AI: “NVIDIA OpenShell open source software traces agent actions and enforces policy at runtime. NVIDIA Sentry adds an independent infrastructure protection layer, and can quarantine a suspicious agent in milliseconds.” “Over 100 organizations from across the AI ecosystem are joining NVIDIA to strengthen AI safety for every industry across the full stack of infrastructure, software, models and robotics”