nemoclaw-user-deploy-remote

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deploy NemoClaw to a Remote GPU Instance

将NemoClaw部署到远程GPU实例

Gotchas

注意事项

The
```
nemoclaw deploy
```
command is deprecated.
On Brev, set
```
CHAT_UI_URL
```
in the launchable environment configuration so it is available when the installer builds the sandbox image.

```
nemoclaw deploy
```
命令已弃用。
在Brev平台上，需在可启动环境配置中设置
```
CHAT_UI_URL
```
，确保安装程序构建沙箱镜像时能访问该变量。

Prerequisites

前提条件

The Brev CLI installed and authenticated.
A provider credential for the inference backend you want to use during onboarding.
```
HF_TOKEN
```
or
```
HUGGING_FACE_HUB_TOKEN
```
exported when your remote vLLM or Hugging Face workflow needs access to gated models.
NemoClaw installed locally if you plan to use the deprecated
```
nemoclaw deploy
```
wrapper. Otherwise, install NemoClaw directly on the remote host after provisioning it.

Run NemoClaw on a remote GPU instance through Brev. The preferred path is to provision the VM, run the standard NemoClaw installer on that host, and then run

nemoclaw onboard

已安装并完成认证的Brev CLI。
初始化过程中使用的推理后端对应的提供商凭证。
当远程vLLM或Hugging Face工作流需要访问受限模型时，需导出
```
HF_TOKEN
```
或
```
HUGGING_FACE_HUB_TOKEN
```
。
若计划使用已弃用的
```
nemoclaw deploy
```
包装器，需在本地安装NemoClaw；否则，可在配置远程主机后直接在该主机上安装NemoClaw。

通过Brev在远程GPU实例上运行NemoClaw。推荐流程为：配置虚拟机，在该主机上运行标准NemoClaw安装程序，然后执行

nemoclaw onboard

。

Quick Start

快速开始

If your Brev instance is already up and has already been onboarded with a sandbox, start with the standard sandbox chat flow:

console

$ nemoclaw my-assistant connect
$ openclaw tui

This gets you into the sandbox shell first and opens the OpenClaw chat UI right away. If the VM is fresh, run the standard installer on that host and then run

nemoclaw onboard

before trying

nemoclaw my-assistant connect

If you are connecting from your local machine and still need to provision the remote VM, you can still use

nemoclaw deploy <instance-name>

as the legacy compatibility path described below.

如果你的Brev实例已启动并完成沙箱初始化，可直接使用标准沙箱聊天流程：

console

$ nemoclaw my-assistant connect
$ openclaw tui

此命令会先进入沙箱shell，然后立即打开OpenClaw聊天UI。如果是全新虚拟机，请先在该主机上运行标准安装程序，再执行

nemoclaw onboard

，之后再尝试

nemoclaw my-assistant connect

。

如果从本地机器连接且仍需配置远程虚拟机，你仍可使用

nemoclaw deploy <instance-name>

作为下文所述的旧版兼容路径。

Deploy the Instance

部署实例

Warning:

The

nemoclaw deploy

command is deprecated. Prefer provisioning the remote host separately, then running the standard NemoClaw installer and

nemoclaw onboard

on that host.

Create a Brev instance and run the legacy compatibility flow:

console

$ nemoclaw deploy <instance-name>

Replace

<instance-name>

with a name for your remote instance, for example

my-gpu-box

. The sandbox created on the remote VM uses

NEMOCLAW_SANDBOX_NAME

, or

my-assistant

when the variable is unset. Sandbox names must be lowercase, start with a letter, contain only letters, numbers, and internal hyphens, and end with a letter or number. The deploy wrapper validates the sandbox name before it provisions the Brev instance, opens SSH, or starts the remote installer.

The legacy compatibility flow performs the following steps on the VM:

Installs Docker and the NVIDIA Container Toolkit if a GPU is present.
Installs the OpenShell CLI.
Runs
```
nemoclaw onboard
```
(the setup wizard) to create the gateway, register providers, and launch the sandbox.
Starts optional host auxiliary services (for example the cloudflared tunnel) when
```
cloudflared
```
is available. Channel messaging is configured during onboarding and runs through OpenShell-managed processes, not through
```
nemoclaw tunnel start
```
.

By default, the compatibility wrapper asks Brev to provision on

gcp

. Override this with

NEMOCLAW_BREV_PROVIDER

if you need a different Brev cloud provider. If you export

HF_TOKEN

HUGGING_FACE_HUB_TOKEN

, the wrapper forwards those values to the VM so remote setup can pull gated Hugging Face model repositories.

警告：

nemoclaw deploy

命令已弃用。建议先单独配置远程主机，再在该主机上运行标准NemoClaw安装程序和

nemoclaw onboard

。

创建Brev实例并运行旧版兼容流程：

console

$ nemoclaw deploy <instance-name>

将

<instance-name>

替换为你的远程实例名称，例如

my-gpu-box

。远程虚拟机上创建的沙箱会使用

NEMOCLAW_SANDBOX_NAME

，若该变量未设置则默认使用

my-assistant

。沙箱名称必须为小写，以字母开头，仅包含字母、数字和中间的连字符，且以字母或数字结尾。部署包装器会在配置Brev实例、打开SSH或启动远程安装程序之前验证沙箱名称。

旧版兼容流程会在虚拟机上执行以下步骤：

若存在GPU，则安装Docker和NVIDIA容器工具包。
安装OpenShell CLI。
执行
```
nemoclaw onboard
```
（设置向导）以创建网关、注册提供商并启动沙箱。
当
```
cloudflared
```
可用时，启动可选的主机辅助服务（例如cloudflared隧道）。通道消息会在初始化过程中配置，并通过OpenShell管理的进程运行，而非通过
```
nemoclaw tunnel start
```
。

默认情况下，兼容包装器会请求Brev在

gcp

上配置实例。若需要其他Brev云提供商，可通过

NEMOCLAW_BREV_PROVIDER

覆盖该设置。若你导出了

HF_TOKEN

或

HUGGING_FACE_HUB_TOKEN

，包装器会将这些值转发到虚拟机，以便远程设置可以拉取受限的Hugging Face模型仓库。

Connect to the Remote Sandbox

连接到远程沙箱

After deployment finishes, the deploy command opens an interactive shell inside the remote sandbox. To reconnect after closing the session, run the command again:

console

$ nemoclaw deploy <instance-name>

部署完成后，deploy命令会在远程沙箱内打开一个交互式shell。关闭会话后如需重新连接，再次运行以下命令即可：

console

$ nemoclaw deploy <instance-name>

Monitor the Remote Sandbox

监控远程沙箱

SSH to the instance and run the OpenShell TUI to monitor activity and approve network requests:

console

$ ssh <instance-name> 'cd ~/nemoclaw && set -a && . .env && set +a && openshell term'

通过SSH连接到实例并运行OpenShell TUI，以监控活动并批准网络请求：

console

$ ssh <instance-name> 'cd ~/nemoclaw && set -a && . .env && set +a && openshell term'

Verify Inference

验证推理功能

Run a test agent prompt inside the remote sandbox:

console

$ openclaw agent --agent main --local -m "Hello from the remote sandbox" --session-id test

在远程沙箱内运行测试代理提示：

console

$ openclaw agent --agent main --local -m "Hello from the remote sandbox" --session-id test

Remote Dashboard Access

远程仪表板访问

The NemoClaw dashboard validates the browser origin against an allowlist baked into the sandbox image at build time. By default the allowlist only contains

http://127.0.0.1:18789

. When accessing the dashboard from a remote browser (for example through a Brev public URL or an SSH port-forward), set

CHAT_UI_URL

to the origin the browser will use before running setup:

console

$ export CHAT_UI_URL="https://openclaw0-<id>.brevlab.com"
$ nemoclaw deploy <instance-name>

For SSH port-forwarding, the origin is typically

http://127.0.0.1:18789

(the default), so no extra configuration is needed.

Warning:

On Brev, set

CHAT_UI_URL

in the launchable environment configuration so it is available when the installer builds the sandbox image. If

CHAT_UI_URL

is not set on a headless host, the compatibility wrapper prints a warning.

NEMOCLAW_DISABLE_DEVICE_AUTH

is also evaluated at image build time. When

CHAT_UI_URL

points at a non-loopback origin, NemoClaw disables OpenClaw device pairing in the generated sandbox configuration because browser-only remote users cannot complete terminal-based pairing. Any device that can reach the configured dashboard origin can connect without pairing, so avoid exposing that origin on internet-reachable or shared-network deployments.

NemoClaw仪表板会在构建沙箱镜像时，将浏览器来源与内置的允许列表进行验证。默认情况下，允许列表仅包含

http://127.0.0.1:18789

。当从远程浏览器访问仪表板时（例如通过Brev公共URL或SSH端口转发），需在运行设置之前将

CHAT_UI_URL

设置为浏览器将使用的来源：

console

$ export CHAT_UI_URL="https://openclaw0-<id>.brevlab.com"
$ nemoclaw deploy <instance-name>

对于SSH端口转发，来源通常为默认的

http://127.0.0.1:18789

，因此无需额外配置。

警告：

在Brev平台上，需在可启动环境配置中设置

CHAT_UI_URL

，确保安装程序构建沙箱镜像时能访问该变量。若在无头主机上未设置

CHAT_UI_URL

，兼容包装器会打印警告信息。

NEMOCLAW_DISABLE_DEVICE_AUTH

也会在镜像构建时被评估。当

CHAT_UI_URL

指向非环回来源时，NemoClaw会在生成的沙箱配置中禁用OpenClaw设备配对，因为仅使用浏览器的远程用户无法完成基于终端的配对。任何能够访问已配置仪表板来源的设备都无需配对即可连接，因此请避免在可访问互联网或共享网络的部署中暴露该来源。

First-Run Readiness Budget

首次运行就绪超时设置

On a remote GPU host, the first

nemoclaw onboard

typically does the slowest work of the lifecycle: the sandbox image is built locally and uploaded into the OpenShell gateway, which can stream hundreds of MiB over the VM's link before the readiness wait even starts. The post-create readiness wait defaults to 180 seconds (

NEMOCLAW_SANDBOX_READY_TIMEOUT

), which is sized for warm-cache, workstation-class onboarding and can be exceeded on:

DGX Station first runs with large quantised models (70B+ parameter footprints, NVFP4 weights).
Cloud VMs where the local image-build cache is cold and the upload runs over the public network.
Hosts onboarding the Brave Web Search preset on the first run (the egress policy stack adds boot work).

Raise the budget before re-running onboard:

console

$ export NEMOCLAW_SANDBOX_READY_TIMEOUT=600
$ nemoclaw onboard

If onboard ends with

Sandbox '<name>' was created but did not become ready within 180s

, onboard deletes the partially-created sandbox first, so the next attempt with the raised budget starts from a clean state. For the inference-probe budget that runs earlier in onboarding, see

NEMOCLAW_LOCAL_INFERENCE_TIMEOUT

(use the

nemoclaw-user-configure-inference

skill).

在远程GPU主机上，首次执行

nemoclaw onboard

通常会完成生命周期中最耗时的工作：沙箱镜像会在本地构建并上传到OpenShell网关，在开始等待就绪状态之前，可能需要通过虚拟机链路传输数百MiB的数据。创建后的就绪等待默认超时时间为180秒（由

NEMOCLAW_SANDBOX_READY_TIMEOUT

控制），该时长是针对缓存已预热的工作站级初始化场景设定的，在以下场景中可能会超时：

DGX Station首次运行大尺寸量化模型（70B+参数规模，NVFP4权重）。
本地镜像构建缓存为空且上传通过公网进行的云虚拟机。
首次运行时初始化Brave Web Search预设的主机（出口策略栈会增加启动工作量）。

重新执行onboard之前，请增加超时时间：

console

$ export NEMOCLAW_SANDBOX_READY_TIMEOUT=600
$ nemoclaw onboard

如果onboard以

Sandbox '<name>' was created but did not become ready within 180s

结束，onboard会先删除部分创建的沙箱，因此下次使用增加后的超时时间尝试时会从干净状态开始。关于onboarding早期运行的推理探测超时设置，请查看

NEMOCLAW_LOCAL_INFERENCE_TIMEOUT

（使用

nemoclaw-user-configure-inference

技能）。

Proxy Configuration

代理配置

NemoClaw routes sandbox traffic through a gateway proxy that defaults to

10.200.0.1:3128

. If your network requires a different proxy, set

NEMOCLAW_PROXY_HOST

and

NEMOCLAW_PROXY_PORT

before onboarding:

console

$ export NEMOCLAW_PROXY_HOST=proxy.example.com
$ export NEMOCLAW_PROXY_PORT=8080
$ nemoclaw onboard

These values are baked into the sandbox image at build time. They are also forwarded into the runtime container during sandbox creation, so

/tmp/nemoclaw-proxy-env.sh

uses the same host and port that the image build used. Only alphanumeric characters, dots, hyphens, and colons are accepted for the host. The port must be numeric (0-65535). Changing the proxy after onboarding requires re-running

nemoclaw onboard

NemoClaw通过网关代理路由沙箱流量，默认代理为

10.200.0.1:3128

。若你的网络需要使用其他代理，请在onboarding之前设置

NEMOCLAW_PROXY_HOST

和

NEMOCLAW_PROXY_PORT

：

console

$ export NEMOCLAW_PROXY_HOST=proxy.example.com
$ export NEMOCLAW_PROXY_PORT=8080
$ nemoclaw onboard

这些值会在构建沙箱镜像时嵌入其中。它们也会在沙箱创建期间转发到运行时容器，因此

/tmp/nemoclaw-proxy-env.sh

会使用与镜像构建时相同的主机和端口。主机仅允许包含字母数字字符、点、连字符和冒号。端口必须为数字（0-65535）。 onboarding后更改代理需要重新执行

nemoclaw onboard

。

GPU Configuration

GPU配置

The deploy script uses the

NEMOCLAW_GPU

environment variable to select the GPU type. The default value is

a2-highgpu-1g:nvidia-tesla-a100:1

. Set this variable before running

nemoclaw deploy

to use a different GPU configuration:

console

$ export NEMOCLAW_GPU="a2-highgpu-1g:nvidia-tesla-a100:2"
$ nemoclaw deploy <instance-name>

部署脚本使用

NEMOCLAW_GPU

环境变量选择GPU类型。默认值为

a2-highgpu-1g:nvidia-tesla-a100:1

。运行

nemoclaw deploy

之前设置该变量可使用不同的GPU配置：

console

$ export NEMOCLAW_GPU="a2-highgpu-1g:nvidia-tesla-a100:2"
$ nemoclaw deploy <instance-name>

References

参考文档

Load references/install-openclaw-plugins.md when users ask how to install, build, or configure OpenClaw plugins under NemoClaw. Explains the difference between OpenClaw plugins and agent skills, and shows the current Dockerfile-based workflow for baking a plugin into a NemoClaw sandbox.
Load references/brev-web-ui.md when a user wants to try NemoClaw without installing the CLI, or asks how to get started on Brev. Guides users through deploying NemoClaw with the Brev web UI.
Load references/sandbox-hardening.md when reviewing sandbox image security controls, auditing capability drops, or looking up the runtime resource limits. Includes the sandbox container image hardening reference, covering Docker capabilities and process limits.

当用户询问如何在NemoClaw下安装、构建或配置OpenClaw插件时，请查看references/install-openclaw-plugins.md。本文解释了OpenClaw插件与代理技能的区别，并展示了当前基于Dockerfile将插件嵌入NemoClaw沙箱的工作流。
当用户希望无需安装CLI即可试用NemoClaw，或询问如何在Brev上快速入门时，请查看references/brev-web-ui.md。本文指导用户通过Brev Web UI部署NemoClaw。
当审查沙箱镜像安全控制、审计权限降级或查找运行时资源限制时，请查看references/sandbox-hardening.md。本文包含沙箱容器镜像加固参考，涵盖Docker权限和进程限制。

nemoclaw-user-deploy-remote

Original

Translation

Deploy NemoClaw to a Remote GPU Instance

将NemoClaw部署到远程GPU实例

Gotchas

注意事项

Prerequisites

前提条件

Quick Start

快速开始

Deploy the Instance

部署实例

Connect to the Remote Sandbox

连接到远程沙箱

Monitor the Remote Sandbox

监控远程沙箱

Verify Inference

验证推理功能

Remote Dashboard Access

远程仪表板访问

First-Run Readiness Budget

首次运行就绪超时设置

Proxy Configuration

代理配置

GPU Configuration

GPU配置

References

参考文档

Related Skills

相关技能