Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

OpenShell

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 5

  1. OpenShell 0.1.x expands runtime controls for autonomous AI agents

    OpenShell announced updates in its 0.1.x line, including a stable release cadence, new isolation primitives, an expanded extension surface, and new APIs. The project says its runtime runs each AI agent in an isolated sandbox, enforces policies on file, system-call, and network access, and limits credentials to approved endpoints. OpenShell also says formal verification flags risky access granted by proposed policy changes before approval.

    Hacker News 首页（100+ 分） · 🔥 0
  2. Nvidia's Huang says the PC must become a personal agent, unveils RTX Spark

    At the Berlin GTC on October 21, Nvidia CEO Jensen Huang said the old "type a command, computer executes" paradigm is over and that PCs must become personal agents that understand user intent and carry out tasks themselves, according to TMTPost. He showed RTX Spark, which Nvidia calls a PC redesigned for the AI era, and said the company worked secretly with Microsoft on the device for four years and invested thousands of "engineer-years". Nvidia's published information says RTX Spark uses a chip design that fuses CPU and GPU with up to 128GB of unified memory and up to 1 petaflop of FP4 AI compute; Huang also brought out Hugging Face MicroDuck robots whose "brains" were built on RTX Spark and which were driven by agents to walk and respond to commands. The report also notes discussion voices arguing that "the PC is only a stopgap" as a host for agents.

    钛媒体 · 🔥 0
  3. NVIDIA launches OpenShell Reference Architecture for secure AI agents

    NVIDIA announced the OpenShell Reference Architecture at GTC Berlin, a full-stack design for building, containing, observing and enforcing safe AI agents on enterprise and edge infrastructure, and said it is now available. It combines OpenShell secure runtime software with Vera Rubin systems for inference, Vera CPUs for agent harnesses and tool use, and BlueField-4 DPUs running NVIDIA Sentry for in-silicon enforcement, extending to RTX Spark, DGX Spark and DGX Station at the edge. NVIDIA says Vera Rubin NVL72 delivers 30x higher throughput per megawatt on agentic workloads and that Sentry stops an agent leaving its boundary in milliseconds while raising agent capacity by up to 20%; those figures are vendor claims not independently measured. Anthropic, AWS, Cisco, CrowdStrike, Dell, Google Cloud, HPE, IBM, Meta, Microsoft, OpenAI, Palo Alto Networks, SAP and ServiceNow are among companies NVIDIA lists as working with the architecture, and Sentry is planned for availability early next year, with DOCA libraries available now.

    NVIDIA Newsroom · 🔥 0
  4. ServiceNow launches AI Passport agent credentials and EmployeeWorks tools

    ServiceNow announced on October 15 new governance controls for AI agents and updates to its EmployeeWorks portal that let employees build specialized assistants and automate routine tasks without writing code. The governance centerpiece is AI Passport, a cryptographically signed credential defining an agent's identity, permitted actions, accessible systems and accountable owner, issued through AI Control Tower and checked as work executes. Nvidia is a design and launch partner, linking AI Passport with its Open Agent Safety Platform, including the OpenShell secure runtime and Sentry security framework. ServiceNow said AI Passport, shadow AI detection and AI Cost Management will be available later this quarter, while the new EmployeeWorks assistants, routines, ToolSmith and Conversations API are in controlled availability.

    SiliconANGLE AI · 🔥 0
  5. Jensen Huang praises OpenClaw for robotics, calls for agent controls via OpenShell

    Nvidia CEO Jensen Huang, speaking at a "Build a Claw" event in London, called OpenClaw "one of the most important models" ever seen and said AI has reached an inflection point where it "has become useful," with agents used for coding, marketing, research assistance and drug discovery. He described OpenClaw as the "first credible" agentic harness, likening it to an exoskeleton for large language models, and said it could bring benefits to robotics, pointing to a robot from Nvidia partner Humanoid. Huang also stressed controls, saying Nvidia created an isolation layer called OpenShell and advocating zero trust, minimum privileges and continuous monitoring, with escalation if an autonomous system exceeds its privileges.

    TechRadar · 🔥 0

Experience and discussion from the community

Share my OpenShell experienceAsk about OpenShell

Nobody has shared their experience with OpenShell yet.