简体中文

NemoClaw vs OpenClaw:你需要 NVIDIA 的沙箱吗?

NemoClaw 不是 OpenClaw 的竞争对手:它把 OpenClaw 放进 NVIDIA 的沙箱中运行。它增加了什么,在内存、渠道和遥测上要付出什么,以及谁需要它。

概览

概览
机器人许可证聊天应用
NemoClawApache-2.02.3万是是Telegram, Discord, Slack免费
OpenClawMIT39.4万是否Telegram, WhatsApp, iMessage, Discord, Slack免费
截至 2026年11月8日 的 GitHub stars

检查清单

检查清单
NemoClawOpenClaw
开源许可证是是
支持本地模型是是
默认沙箱隔离是否
默认无遥测否否
接入你的聊天应用是是
你离开时也能工作是是

这不是二选一的问题。NemoClaw 并不是一个独立的智能体:它是 NVIDIA 的开源技术栈,把 OpenClaw(或 Hermes Agent,或 LangChain Deep Agents Code)安装进一个 OpenShell 沙箱容器,并为其加上各种管控。运行 NemoClaw 时,你运行的仍然是 OpenClaw。真正的问题是:你想让 OpenClaw 跑在主机上,还是关在 NVIDIA 的笼子里。背景信息请参阅 NemoClaw 是什么和 OpenClaw 是什么。

NemoClaw high-level component diagram: users and operators, NemoClaw control (CLI, installer, dashboard), the OpenShell gateway, the sandbox running OpenClaw, inference, integrations and state
How NemoClaw wraps an agent in an OpenShell sandboxgithub.com

NemoClaw 增加了什么

单独的 OpenClaw 运行在你的机器上,沙箱默认关闭。除非你开启审批或沙箱,否则它可以在主机上运行命令,并能广泛访问邮件、消息和文件。这正是 NemoClaw 要填补的空白:

  • 网络策略。 未经批准的目标会被拦截并提交给操作员审批,从而限制被提示注入的智能体能把你的数据发往何处。
  • 沙箱内的文件系统和进程管控。
  • 凭据托管。 推理、消息和 MCP 凭据由沙箱外的 OpenShell 网关持有。WhatsApp 这类二维码配对会话是例外,其会话凭据保存在沙箱内。
  • 引导式上手流程、一个 CLI 和一个仪表盘。
  • 托管推理,通过 OpenShell 路由到 NVIDIA Endpoints、其他托管提供商,或通过 Ollama、vLLM 或 NVIDIA NIM 运行的本地模型。
WhatsApp chat with an OpenClaw assistant giving casual travel advice to a user in Marrakech
Chatting with OpenClaw in WhatsAppdocs.openclaw.ai

它的代价

硬件。 NemoClaw 要求 4 个 vCPU、8 GB 内存(推荐 16 GB)、20 GB 可用磁盘空间和一个容器运行时(Docker、Docker Desktop 或 Colima),外加一个 2.4 GB 的沙箱镜像。单独的 OpenClaw 只需要 Node 24.16+ 或 26.1+,可通过脚本、npm、桌面应用、Docker 或 Railway 一键部署安装。

平台。 NemoClaw 主要的测试平台是 Linux 和 DGX Spark。Apple Silicon 上的 macOS 以及通过 WSL2 的 Windows 可以运行,但有限制。OpenClaw 有适用于 macOS、Windows、Linux、iOS 和 Android 的原生应用。

渠道。 OpenClaw 支持 29 个聊天渠道。NemoClaw 在上手流程中配置 Telegram、Discord 和 Slack,并把 WhatsApp、Microsoft Teams、Google Chat 和 WeChat 标记为实验性。其中不包括 iMessage。

成熟度。 NVIDIA 称 NemoClaw 处于 alpha 阶段,并以尽力而为的方式提供支持。机器人实际能做什么,仍取决于其中的 OpenClaw 版本。

遥测。 换过去也躲不开。OpenClaw 会发送带有版本和系统信息的每日更新检查,除非你设置 update.checkOnStart: false。NemoClaw 的 CLI 和安装程序会向 NVIDIA 发送操作遥测,除非你设置 NEMOCLAW_DISABLE_TELEMETRY=1。如果你在意,两个都要设置。

许可证与成本

OpenClaw 采用 MIT,NemoClaw 采用 Apache-2.0。两者都免费;除非你运行本地模型,否则无论选哪个都要向模型提供商付费。NemoClaw 经过测试的 DGX Spark 路径,使它更适合本来就拥有 NVIDIA 硬件来做本地推理的人。

结论

  • 直接运行 OpenClaw:如果是在个人笔记本或台式机上、在 Mac 上,或可用内存不足 8 GB,并且你依赖 iMessage 或手机应用。在连接邮箱之前先开启它的沙箱和审批。
  • 在 NemoClaw 中运行 OpenClaw:如果你要在 Linux 服务器或 DGX Spark 上运行一个会接触真实账号的常驻智能体,尤其是需要有人审批每一个新网络目标的场景。作为交换,要接受 alpha 软件和更少的渠道。
  • 两者都不选:如果你想要隔离又不想要那么重:ZeroClaw 在单个二进制文件中默认开启操作系统沙箱,NanoClaw 则把每个智能体放进各自的容器。更多选择请见我们的 OpenClaw 替代品。

价格

NemoClaw

NemoClaw: 价格
Open source免费
  • Apache-2.0, free to self-host
  • You pay for inference from the provider you route to, or run a local model

OpenClaw

OpenClaw: 价格
Open source免费
  • MIT licensed; no subscription, hosted tier or paid edition
  • You pay your chosen model provider, or run a local model
  • Desktop apps for macOS, Windows and Linux

NemoClaw

优点

  • Puts OpenClaw or Hermes Agent in a sandbox with network, filesystem and process controls instead of running it on your host
  • Unapproved network destinations are blocked and surfaced for an operator to approve
  • Inference, messaging and MCP credentials stay outside the sandbox
  • Backed by NVIDIA, with local inference through Ollama, vLLM or NIM and a tested path on DGX Spark

缺点

  • Alpha: maintainers support it on a best-effort basis, and several channels are experimental
  • A wrapper, not an agent: what the bot can do depends on the OpenClaw or Hermes version inside
  • Heavier than running the agent alone: 8 GB RAM minimum, a 2.4 GB sandbox image and a container runtime
  • The CLI sends operation telemetry to NVIDIA unless you set NEMOCLAW_DISABLE_TELEMETRY=1

OpenClaw

优点

  • Free and MIT licensed, with no paid tier
  • Runs on your own hardware, and state, memory and credentials stay there
  • Works in 29 chat channels, including WhatsApp, Telegram, iMessage, Slack, Discord and Microsoft Teams
  • Model-agnostic: 64 model and media providers, plus local models
  • Large ecosystem of skills and 142 official plugins, and very active development

缺点

  • Model costs are on you and can run high: testers and users have reported spending over $100 in a day with expensive models
  • Sandboxing is off by default and the agent can run commands on the host unless you turn on approvals
  • Setup and upkeep expect comfort with the command line; maintainers warn it is risky for non-technical users
  • Broad access to email, messages and the system makes prompt injection and malicious third-party skills a real risk

功能

功能
NemoClawOpenClaw
联网搜索是是
图像生成未知是
语音模式未知是
文件上传未知是
记忆未知是
代你执行操作是是
应用集成是是
自主运行是是
主动给你发消息未知是
可运行多个机器人未知是

来源

NemoClaw

  1. NVIDIA/NemoClaw on GitHub (Apache-2.0, README: supported agents, alpha status)
  2. NemoClaw docs: Overview
  3. NemoClaw docs: Prerequisites and platforms
  4. NemoClaw docs: Choose an inference provider (Ollama, vLLM, NIM)
  5. NemoClaw docs index: messaging channels (WhatsApp, Teams, Google Chat, WeChat experimental)
  6. NemoClaw source: telemetry delivery and NEMOCLAW_DISABLE_TELEMETRY

OpenClaw

  1. OpenClaw homepage and Foundation section
  2. OpenClaw integrations: channels, providers and plugins
  3. openclaw/openclaw on GitHub (MIT, v2026.11.1)
  4. OpenClaw docs: Sandboxing (off by default)
  5. Wikipedia: OpenClaw
  6. Notebookcheck: OpenClaw can burn through hundreds of dollars per day
  7. OpenClaw docs: Memory overview
  8. OpenClaw docs: Automations
  9. OpenClaw docs: Chat channels
  10. OpenClaw docs: iMessage
  11. OpenClaw docs: Heartbeat, now a default Proactive check job
  12. OpenClaw docs: Multi-agent routing
  13. OpenClaw docs: Platforms (macOS, Windows, Linux, iOS and Android apps)
  14. OpenClaw docs: Tools (exec, browser, web search)
  15. OpenClaw docs: Audio and voice notes (inbound transcription)
  16. OpenClaw docs: Image and media support (inbound media)
  17. OpenClaw docs: Install (system requirements, installer script, npm, desktop apps, Docker)
  18. OpenClaw docs: One-click deploy on Railway
  19. OpenClaw docs: Usage telemetry and update checks (on by default, feature statistics opt-in)
  20. OpenClaw docs: Ollama provider (local models)