OpenShell v0.0.26 🖥️ openshell-vm: libkrun-based microVM gateway 📄 docs on Fern 🧩 modular gRPC server refactor 🧪 dedicated GPU CI workflows 🧹 docs structure + nav cleanup Run agents in isolated microVMs, not just processes. https://github.com/NVIDIA/OpenShell/releases/tag/v0.0.26
中文: OpenShell v0.0.26 🖥️ openshell-vm:基于 libkrun 的 microVM 网关 📄 蕨类植物 🧩 模块化 GRPC 服务器重构 🧪 专用 GPU CI 工作流 🧹 文档结构 + 导航清理 在孤立的微虚拟机中运行代理,而不仅仅是进程。
🙌 Andrej Karpathy’s lab has received the first DGX Station GB300 -- a Dell Pro Max with GB300. 💚 We can't wait to see what you’ll create @karpathy! 🔗 https://blogs.nvidia.com/blog/gtc-2026-news/#dgx-station @DellTech https://twitter.com/NVIDIAAIDev/status/2034291235041554871/photo/1
中文: 安德烈·卡帕蒂实验室已接收了首台DGX Station GB300——配备GB300的戴尔Pro Max。 💚 我们迫不及待想看看你将创建 @karpathy! 🔗 @DellTech
@muccadevx 💚By popular demand on this thread, we will name our green lobster, "Shelly." @Baxate https://twitter.com/NVIDIAAIDev/status/2033637455279362251/photo/1
中文: @muccadevx 💚 根据这条帖子的热门需求,我们将给我们的绿色龙虾取名:“Shelly”。@Baxate
🦞These innovations come together to create a model that is well suited for long-running autonomous agents. On PinchBench—a benchmark for evaluating LLMs as @OpenClaw coding agents—Nemotron 3 Super scores 85.6% across the full test suite, making it the best open model in its… https://twitter.com/NVIDIAAIDev/status/2031774925522940048/photo/1
中文: 这些创新结合在一起,创造出一种非常适合长期运行的自主代理的模型。 在PinchBench上——作为将LLM作为@OpenClaw编码代理进行评估的基准——Nemotron 3 Super 在完整测试套件中得分为 85.6%,使其成为其最佳开放模式......