Nvidia, Vast Data announce AI agent sandbox. Vast Data, a New York-headquartered data infrastructure company, announced an AI agent sandbox stack with Nvidia on 22 October 2026 for production deployments that need persistent agent state and activity records. The stack combines Vast's AI Operating System with Nvidia NemoClaw and OpenShell. Vast said OpenShell provides isolated execution and policy enforcement, while its platform supplies persistent storage and state across sessions. According to Vast, the system keeps records of agent activity, including tool calls, prompts, token use, costs, and decisions, even after an agent stops running. The company plans to demonstrate the setup at Nvidia GTC Berlin and make automated deployment available through a public GitHub repository. The announcement comes as the European Union AI Act requires records and mandates logs for certain high-risk AI systems. AI agent observability is also emerging as an enterprise software category, with tools being compared for production use. Recent VAST data developments. Stay updated on the go with our mobile app. Get latest insights with smoother, more personalized experience through TIA mobile app. How would you feel if you could no longer use Tech in Asia? Share, tag us, and land on our Wall of!

VAST agent sandbox stores cross-session persistent agent state. Chris Mellor STORAGE EDITOR Blocks & Files editor Published wed 21 Oct 2026 // 14:46 UTC VAST Data is using Nvidia NemoClaw and newly-announced OpenShell to persist AI agent state with a record of tool calls, prompts, tokens, costs and decisions, while agent compute stay ephemeral. Nvidia OpenShell is an open, secure runtime for AI agents, governing agent execution, access, and where inference goes, giving agents the access they need to execute the tasks they're sent. It combines sandboxed execution, controlled resource access, credential protection, and formal policy verification, with enforcement outside the agent workload. It's integrated with hardware-level security mechanisms based on the BlueField-4 chip. NemoClaw is an open-source collection of blueprints and a reference stack for deploying specialized, always-on autonomous AI agents more safely and with governance controls. Agent state persistence is the core feature of VAST's new Foundation Stack for Governed Agent Sandboxes (FSGAS), announced at Nvidia GTC in Berlin. Alon Horev, CTO and Co-Founder at VAST Data, said: "Every enterprise that puts an agent into production will eventually need to answer what it did and why it did it. An agent might exist for minutes, spawn thousands of other agents and then disappear, but its work has to persist and its actions have to stay understandable long afterward. Together with Nvidia, we're showing how the VAST AI Operating System provides the durable foundation underneath secure agent environments, so organisations can scale agentic systems without sacrificing persistence, governance or control." A VAST blog states: "Agent sandboxes are quickly becoming the de facto approach for implementing guardrails around AI agents. Sandboxes should prevent agents from going rogue and limit the blast radius of any questionable actions, while still providing agents access to all the tools they need. Nvidia's Kari Briski, VP of Generative AI Software, added more context: "As AI agents take on more complex work, enterprises need infrastructure that can support secure execution while preserving the data, context, and state agents depend on across their lifecycle. By combining Nvidia NemoClaw and OpenShell with the VAST AI Operating System, organisations can build agent sandbox environments that are secure and designed to scale from experimentation to production." FSGAS uses a new Agent Sandbox Foundation Stack, and VAST says agents can spawn other agents, execute tasks and disappear, with fleets creating and destroying thousands of isolated workspaces an hour. Long-running agents may also work across multiple sessions, sleeping, resuming and delegating tasks to short-lived subagents along the way. Whether an agent runs for minutes or across multiple sessions, its progress, working data and memory need to persist independently of any individual sandbox or compute node - remaining available, governed and auditable wherever execution resumes. FSGAS provides a scalable, persistent data infrastructure that enterprises need to securely run thousands of AI agents and sub-agents in production. It works like this; * As new agent tasks are initiated, VAST uses zero-copy clones to provision persistent storage for isolated OpenShell sandboxes without creating full copies of the underlying data. VAST separates agent execution from persistent state so agents can pause, resume or transfer work across agent environments without starting from scratch. * VAST DataBase maintains a persistent record of agent activity, including tool calls, prompts, tokens, costs and decisions while the VAST Management System provides real-time visibility into data flows and infrastructure activity across agent fleets. By decoupling persistent agent state from individual compute nodes, the FSGAS architecture allows agents to pause, resume, or move across eligible infrastructure without losing their progress, working data or context. * Enterprise research assistance with Nvidia Nemotron - AI-Q based Foundation Stack provides a foundation for building custom AI researchers that can operate across private, enterprise data sources, synthesising hours of research in minutes, using the VAST AI OS for persistent and secure context, scalable reasoning pipelines, and trusted agent execution., * Video intelligence with Nvidia Cosmos - a Video Search and Summarisation (VSS)-based Foundation Stack enables organisations to ingest massive volumes of live or archived video and extract insights through semantic indexing, summarisation, and interactive Q&A, VAST plans to make the automated deployment available through a public GitHub repository, providing a reproducible path for organisations to deploy the architecture in their own environments. The aforementioned blog notes: "This foundation stack builds on the recently announced VAST DataEnclave, which delivers a trusted and cryptographically secured runtime for running leading commercial AI models alongside sensitive data on customer-controlled infrastructure." Read more here; it's worthwhile. Bootnote. HPE will support the Nvidia OpenShell Reference Architecture for Safe Agents, delivering full-stack AI factory governance, isolation, and security with Nvidia Vera Rubin, Nvidia Vera CPUs, and Nvidia BlueField-4.

Mirantis has integrated its k0rdent AI orchestration software with VAST Data's AI Operating System. The aim is to help neoclouds, telecoms, and other GPU-as-a-service providers run secure, multi-tenant AI infrastructure at scale. k0rdent AI can now automatically provision, scale, and retire tenant-isolated VAST storage alongside compute. Operators previously had to coordinate servers, Kubernetes clusters, storage, and tenant access by hand, which invited configuration errors. Mirantis says the integration cuts tenant onboarding from weeks to minutes. It plans to extend the approach to more technology partners. The companies first announced their collaboration in February 2026, when Mirantis joined VAST Data's Cosmos Partner Program.