NVIDIA 发布 NemoClaw 开放蓝图，构建可控栈专用智能体
原标题：Build Specialized Agents on a Stack You Control with NVIDIA NemoClaw
AI 摘要
NVIDIA 发布 NemoClaw 开放蓝图，帮助开发者在自有可控的技术栈上构建专用智能体。NemoClaw 本身不是 harness 或运行时，而是将调优后的开源 harness（OpenClaw、Hermes Agent、LangChain Deep Agents）、Nemotron 开源模型、NeMo 优化工具与 OpenShell 安全运行时组合成完整栈。文中称 LangChain 针对 Nemotron 3 Ultra 调优 Deep Agents harness 后，在无需重训模型的情况下达到接近前沿的性能，单次运行成本约为领先闭源模型的十分之一。
正文节选
Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces policies, along with optimization and observability tools for reliable execution. For production agents, the challenge lies in making these agents capable and safe to operate with access to real enterprise systems and data. This post explains how these components work together, with a focus on how NVIDIA NemoClaw open blueprints enable dev