nemoclaw-user-get-started

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

NemoClaw Quickstart with OpenClaw

基于OpenClaw的NemoClaw快速入门

Follow these steps to get started with NemoClaw and your first sandboxed OpenClaw agent.

Note:

Make sure you have completed reviewing the Prerequisites (use the

nemoclaw-user-get-started

skill) before following this guide.

按照以下步骤开始使用NemoClaw和你的首个沙箱化OpenClaw Agent。

注意：

在遵循本指南之前，请确保已完成对先决条件的检查（使用

nemoclaw-user-get-started

技能）。

Install NemoClaw and Onboard OpenClaw Agent

安装NemoClaw并入门OpenClaw Agent

Download and run the installer script. The script installs Node.js if it is not already present, then runs the guided onboard wizard to create a sandbox, configure inference, and apply security policies.

Note:

NemoClaw creates a fresh OpenClaw instance inside the sandbox during the onboarding process.

bash

curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash

The piped installer prompts through your terminal. In headless scripts or CI, pass explicit acceptance to the

bash

side of the pipe:

console

$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | NEMOCLAW_NON_INTERACTIVE=1 NEMOCLAW_ACCEPT_THIRD_PARTY_SOFTWARE=1 bash

If you use nvm or fnm to manage Node.js, the installer might not update your current shell's PATH. If

nemoclaw

is not found after install, run

source ~/.bashrc

(or

source ~/.zshrc

for zsh) or open a new terminal.

On Linux, the installer checks Docker before it installs NemoClaw. If Docker is missing, the installer downloads the official Docker convenience script, asks for

sudo

, installs Docker, and starts the Docker service when systemd is available. If Docker is installed but your current shell cannot use the Docker socket yet, the installer adds your user to the

docker

group when needed and exits with a recovery command.

On macOS, the installer uses the Docker-driver OpenShell gateway path with Docker Desktop or Colima.

console

$ newgrp docker
$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash

On DGX Spark, DGX Station, and Windows WSL, an interactive installer offers express install after you accept the third-party software notice. Express install switches onboarding to non-interactive mode, allows

sudo

password prompts for required host changes, applies the suggested security policy, and selects the managed local inference path for that platform. On WSL, express install selects the Windows-host Ollama setup path. Set

NEMOCLAW_NO_EXPRESS=1

to skip the express prompt, or set

NEMOCLAW_PROVIDER

before launching the installer when you want to choose a provider yourself.

The installer auto-launches

nemoclaw onboard

when it can locate the freshly-installed binary. If it cannot locate the binary, or if blocking host preflight checks fail, it does not launch the wizard automatically. In that case, the installer prints the relevant diagnostics and a

To finish setup, run:

block with the explicit

nemoclaw onboard

command.

Note:

The onboard flow builds the sandbox image with

NEMOCLAW_DISABLE_DEVICE_AUTH=1

so the dashboard is immediately usable during setup. This is a build-time setting baked into the sandbox image, not a runtime knob. If you export

NEMOCLAW_DISABLE_DEVICE_AUTH

after onboarding finishes, it has no effect on an existing sandbox.

下载并运行安装脚本。该脚本会在未安装Node.js的情况下自动安装它，然后运行引导式入门向导来创建沙箱、配置推理并应用安全策略。

注意：

在入门过程中，NemoClaw会在沙箱内创建一个全新的OpenClaw实例。

bash

curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash

管道安装程序会在终端中提示操作。在无头脚本或CI环境中，需向管道的

bash

端传递明确的接受参数：

console

$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | NEMOCLAW_NON_INTERACTIVE=1 NEMOCLAW_ACCEPT_THIRD_PARTY_SOFTWARE=1 bash

如果你使用nvm或fnm管理Node.js，安装程序可能不会更新当前Shell的PATH。如果安装后找不到

nemoclaw

命令，请运行

source ~/.bashrc

（zsh用户请运行

source ~/.zshrc

）或打开新终端。

在Linux系统上，安装程序会在安装NemoClaw之前检查Docker。如果缺少Docker，安装程序会下载官方Docker便捷脚本，请求

sudo

权限，安装Docker，并在systemd可用时启动Docker服务。如果已安装Docker但当前Shell无法使用Docker套接字，安装程序会在需要时将你的用户添加到

docker

组，并退出时提供恢复命令。

在macOS系统上，安装程序会使用Docker-driver OpenShell网关路径，搭配Docker Desktop或Colima使用。

console

$ newgrp docker
$ curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash

在DGX Spark、DGX Station和Windows WSL上，交互式安装程序会在你接受第三方软件通知后提供快速安装选项。快速安装会将入门流程切换为非交互模式，允许

sudo

密码提示以进行必要的主机更改，应用建议的安全策略，并为该平台选择托管本地推理路径。在WSL上，快速安装会选择Windows主机端的Ollama设置路径。设置

NEMOCLAW_NO_EXPRESS=1

可跳过快速安装提示，或者在启动安装程序前设置

NEMOCLAW_PROVIDER

来自行选择提供商。

当安装程序可以找到新安装的二进制文件时，会自动启动

nemoclaw onboard

。如果无法找到二进制文件，或者主机预检检查失败，则不会自动启动向导。在这种情况下，安装程序会打印相关诊断信息以及一个“完成设置，请运行：”的区块，其中包含明确的

nemoclaw onboard

命令。

注意：

入门流程会使用

NEMOCLAW_DISABLE_DEVICE_AUTH=1

构建沙箱镜像，以便在设置过程中立即使用仪表板。这是一个嵌入到沙箱镜像中的构建时设置，而非运行时参数。如果在入门完成后导出

NEMOCLAW_DISABLE_DEVICE_AUTH

，它对现有沙箱不会产生任何影响。

Respond to the Onboard Wizard

响应入门向导

After the installer launches

nemoclaw onboard

, the wizard runs preflight checks, starts or reuses the OpenShell gateway, and asks for an inference provider, sandbox name, optional web search, optional messaging channels, and network policy presets. At any prompt, press Enter to accept the default shown in

[brackets]

, type

back

to return to the previous prompt, or type

exit

to quit. If existing sandbox sessions are running, the installer warns before onboarding because the setup can rebuild or upgrade sandboxes after the new sandbox launches.

The inference provider prompt presents a numbered list.

text

  1) NVIDIA Endpoints
  2) OpenAI
  3) Other OpenAI-compatible endpoint
  4) Anthropic
  5) Other Anthropic-compatible endpoint
  6) Google Gemini
  7) Local Ollama (localhost:11434)
  8) Model Router (experimental)
  Choose [1]:

Pick the option that matches where you want inference traffic to go, then expand the matching helper below for the follow-up prompts and the API key environment variable to set. For the full list of providers and validation behavior, refer to Inference Options (use the

nemoclaw-user-configure-inference

skill). Local Ollama appears when NemoClaw detects a usable local Ollama path or can offer an install or start action for your platform. The Model Router option appears when the blueprint router profile is enabled.

Tip:

Export the API key before launching the installer so the wizard does not have to ask for it. For example, run

export NVIDIA_API_KEY=<your-key>

before

curl ... | bash

. If you entered a key incorrectly, refer to Reset a Stored Credential (use the

nemoclaw-user-manage-sandboxes

skill) to clear and re-enter it.

Option 1: NVIDIA Endpoints:

Routes inference to models hosted on build.nvidia.com.

Use

NVIDIA_API_KEY

for the API key. Get one from the NVIDIA build API keys page.

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, press Enter (or type
```
1
```
) to select NVIDIA Endpoints.
At the
```
NVIDIA_API_KEY:
```
prompt, paste your key if it is not already exported.
At the
```
Choose model [1]:
```
prompt, pick a curated model from the list (for example,
```
Nemotron 3 Super 120B
```
,
```
GLM-5
```
,
```
MiniMax M2.7
```
,
```
GPT-OSS 120B
```
, or
```
DeepSeek V4 Pro
```
), or pick
```
Other...
```
to enter any model ID from the NVIDIA Endpoints catalog.

NemoClaw validates the model against the catalog API before creating the sandbox.

Tip:

Use this option for Nemotron and other models hosted on

build.nvidia.com

. If you run NVIDIA Nemotron from a self-hosted NIM, an enterprise gateway, or any other endpoint, choose Option 3 instead, since all Nemotron models expose OpenAI-compatible APIs.

Option 2: OpenAI:

Routes inference to the OpenAI API at

https://api.openai.com/v1

Use

OPENAI_API_KEY

for the API key. Get one from the OpenAI API keys page.

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, type
```
2
```
to select OpenAI.
At the
```
OPENAI_API_KEY:
```
prompt, paste your key if it is not already exported.
At the
```
Choose model [1]:
```
prompt, pick a curated model (for example,
```
gpt-5.4
```
,
```
gpt-5.4-mini
```
,
```
gpt-5.4-nano
```
, or
```
gpt-5.4-pro-2026-03-05
```
), or pick Other... to enter any OpenAI model ID.

Option 3: Other OpenAI-Compatible Endpoint:

Routes inference to any server that implements

/v1/chat/completions

, including OpenRouter, LocalAI, llama.cpp, vLLM behind a proxy, and any compatible gateway.

Use

COMPATIBLE_API_KEY

for the API key. Set it to whatever credential your endpoint expects. If your endpoint does not require auth, use any non-empty placeholder.

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, type
```
3
```
to select Other OpenAI-compatible endpoint.
At the
```
OpenAI-compatible base URL
```
prompt, enter the provider's base URL. Find the exact value in your provider's API documentation. NemoClaw appends
```
/v1
```
automatically, so leave that suffix off.
At the
```
COMPATIBLE_API_KEY:
```
prompt, paste your key if it is not already exported.
At the
```
Other OpenAI-compatible endpoint model []:
```
prompt, enter the model ID exactly as it appears in your provider's model catalog.

For example, when you use NVIDIA's OpenAI-compatible inference endpoint, enter

https://inference-api.nvidia.com

as the base URL and the model ID your endpoint exposes, such as

openai/openai/gpt-5.5

NemoClaw sends a real inference request to validate the endpoint and model. If the endpoint does not return the streaming events OpenClaw needs from the Responses API, NemoClaw falls back to the chat completions API and configures OpenClaw to use

openai-completions

Tip:

NVIDIA Nemotron models expose OpenAI-compatible APIs, so this option is the right choice for any Nemotron deployment that does not live on

build.nvidia.com

. Common examples include a self-hosted NIM container, an enterprise NVIDIA AI Enterprise gateway, or a vLLM/SGLang server running Nemotron weights. Point the base URL at your endpoint and enter the Nemotron model ID exactly as your server reports it.

Option 4: Anthropic:

Routes inference to the Anthropic Messages API at

https://api.anthropic.com

Use

ANTHROPIC_API_KEY

for the API key. Get one from the Anthropic console keys page.

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, type
```
4
```
to select Anthropic.
At the
```
ANTHROPIC_API_KEY:
```
prompt, paste your key if it is not already exported.
At the
```
Choose model [1]:
```
prompt, pick a curated model (for example,
```
claude-sonnet-4-6
```
,
```
claude-haiku-4-5
```
, or
```
claude-opus-4-6
```
), or pick Other... to enter any Claude model ID.

Option 5: Other Anthropic-Compatible Endpoint:

Routes inference to any server that implements the Anthropic Messages API at

/v1/messages

, including Claude proxies, Bedrock-compatible gateways, and self-hosted Anthropic-compatible servers.

Use

COMPATIBLE_ANTHROPIC_API_KEY

for the API key. Set it to whatever credential your endpoint expects.

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, type
```
5
```
to select Other Anthropic-compatible endpoint.
At the
```
Anthropic-compatible base URL
```
prompt, enter the proxy or gateway's base URL from its documentation.
At the
```
COMPATIBLE_ANTHROPIC_API_KEY:
```
prompt, paste your key if it is not already exported.
At the
```
Other Anthropic-compatible endpoint model []:
```
prompt, enter the model ID exactly as it appears in your gateway's model catalog.

Option 6: Google Gemini:

Routes inference to Google's OpenAI-compatible Gemini endpoint at

https://generativelanguage.googleapis.com/v1beta/openai/

Use

GEMINI_API_KEY

for the API key. Get one from Google AI Studio API keys.

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, type
```
6
```
to select Google Gemini.
At the
```
GEMINI_API_KEY:
```
prompt, paste your key if it is not already exported.

At the

Choose model [5]:

prompt, pick a curated model (for example,

gemini-3.1-pro-preview

gemini-3.1-flash-lite-preview

gemini-3-flash-preview

gemini-2.5-pro

gemini-2.5-flash

, or

gemini-2.5-flash-lite

), or pick Other... to enter any Gemini model ID.

Option 7: Local Ollama:

Routes inference to a local Ollama instance. Depending on your platform, the wizard can use an existing daemon, start an installed daemon, or offer an install action.

No API key is required. On non-WSL hosts, NemoClaw generates a token and starts an authenticated proxy so containers can reach Ollama without exposing the daemon directly to your network. On WSL, NemoClaw can also use Ollama on the Windows host through

host.docker.internal

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, type
```
7
```
to select Local Ollama.
At the
```
Choose model [1]:
```
prompt, pick from Ollama models if any are already installed. If none are installed, pick a starter model to pull and load now, or pick Other... to enter any Ollama model ID.

For setup details, including GPU recommendations and starter model choices, refer to Use a Local Inference Server (use the

nemoclaw-user-configure-inference

skill).

Option 8: Model Router:

Starts a host-side model router and routes sandbox inference through OpenShell to that router. The router chooses from the model pool in

nemoclaw-blueprint/router/pool-config.yaml

for each request.

Use

NVIDIA_API_KEY

for the model pool credentials.

Respond to the wizard as follows.

At the
```
Choose [1]:
```
prompt, type
```
8
```
to select Model Router (experimental).
At the
```
NVIDIA_API_KEY:
```
prompt, paste your key if it is not already exported.
Review the configuration summary and continue with the sandbox build.

For scripted setup, set:

console

$ NEMOCLAW_PROVIDER=routed NVIDIA_API_KEY=<your-key> nemoclaw onboard --non-interactive

The router listens on the host at port

. The sandbox still calls

https://inference.local/v1

, so do not point in-sandbox tools at the host router port directly.

Local NIM and Local vLLM:

Local NVIDIA NIM appears when
```
NEMOCLAW_EXPERIMENTAL=1
```
is set and the host has a NIM-capable GPU. NemoClaw pulls and manages a NIM container.
Local vLLM (already running) appears whenever NemoClaw detects a vLLM server on
```
localhost:8000
```
. No flag is required for the menu entry. NemoClaw auto-detects the loaded model.
Local vLLM (managed install/start) appears by default on DGX Spark and DGX Station. Generic Linux NVIDIA GPU hosts require
```
NEMOCLAW_EXPERIMENTAL=1
```
or
```
NEMOCLAW_PROVIDER=install-vllm
```
. NemoClaw pulls and starts a vLLM container on supported hosts.

For setup, refer to Use a Local Inference Server (use the

nemoclaw-user-configure-inference

skill).

安装程序启动

nemoclaw onboard

后，向导会运行预检检查、启动或重用OpenShell网关，并询问推理提供商、沙箱名称、可选的网页搜索、可选的消息渠道以及网络策略预设。在任何提示下，按Enter键接受

[方括号]

中显示的默认值，输入

back

返回上一个提示，或输入

exit

退出。如果已有沙箱会话在运行，安装程序会在入门前发出警告，因为新沙箱启动后，设置过程可能会重建或升级沙箱。

推理提供商提示会显示一个编号列表。

text

  1) NVIDIA Endpoints
  2) OpenAI
  3) Other OpenAI-compatible endpoint
  4) Anthropic
  5) Other Anthropic-compatible endpoint
  6) Google Gemini
  7) Local Ollama (localhost:11434)
  8) Model Router (experimental)
  Choose [1]:

选择与你希望推理流量前往的位置匹配的选项，然后展开下方对应的帮助内容，了解后续提示和需要设置的API密钥环境变量。有关提供商的完整列表和验证行为，请参考推理选项（使用

nemoclaw-user-configure-inference

技能）。当NemoClaw检测到可用的本地Ollama路径，或可为你的平台提供安装或启动操作时，会显示Local Ollama选项。当蓝图路由器配置文件启用时，会显示Model Router选项。

提示：

在启动安装程序之前导出API密钥，这样向导就无需询问。例如，在运行

curl ... | bash

之前，先运行

export NVIDIA_API_KEY=<你的密钥>

。如果你输入的密钥有误，请参考重置存储的凭据（使用

nemoclaw-user-manage-sandboxes

技能）来清除并重新输入。

选项1：NVIDIA Endpoints：

将推理路由到托管在build.nvidia.com上的模型。

使用

NVIDIA_API_KEY

作为API密钥。可从NVIDIA build API密钥页面获取。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，按Enter键（或输入
```
1
```
）选择NVIDIA Endpoints。
在
```
NVIDIA_API_KEY:
```
提示下，如果尚未导出密钥，请粘贴你的密钥。
在
```
Choose model [1]:
```
提示下，从列表中选择一个精选模型（例如
```
Nemotron 3 Super 120B
```
、
```
GLM-5
```
、
```
MiniMax M2.7
```
、
```
GPT-OSS 120B
```
或
```
DeepSeek V4 Pro
```
），或选择
```
Other...
```
输入NVIDIA Endpoints目录中的任何模型ID。

NemoClaw会在创建沙箱之前验证模型是否存在于目录API中。

提示：

此选项适用于托管在

build.nvidia.com

上的Nemotron和其他模型。如果你从自托管的NIM、企业网关或任何其他端点运行NVIDIA Nemotron，请选择选项3，因为所有Nemotron模型都暴露OpenAI兼容的API。

选项2：OpenAI：

将推理路由到位于

https://api.openai.com/v1

的OpenAI API。

使用

OPENAI_API_KEY

作为API密钥。可从OpenAI API密钥页面获取。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，输入
```
2
```
选择OpenAI。
在
```
OPENAI_API_KEY:
```
提示下，如果尚未导出密钥，请粘贴你的密钥。
在
```
Choose model [1]:
```
提示下，选择一个精选模型（例如
```
gpt-5.4
```
、
```
gpt-5.4-mini
```
、
```
gpt-5.4-nano
```
或
```
gpt-5.4-pro-2026-03-05
```
），或选择**Other...**输入任何OpenAI模型ID。

选项3：其他OpenAI兼容端点：

将推理路由到任何实现

/v1/chat/completions

的服务器，包括OpenRouter、LocalAI、llama.cpp、代理后的vLLM以及任何兼容的网关。

使用

COMPATIBLE_API_KEY

作为API密钥。将其设置为你的端点所需的任何凭据。如果你的端点不需要身份验证，请使用任何非空占位符。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，输入
```
3
```
选择Other OpenAI-compatible endpoint。
在
```
OpenAI-compatible base URL
```
提示下，输入提供商的基础URL。可在提供商的API文档中找到确切值。NemoClaw会自动追加
```
/v1
```
，因此请不要包含该后缀。
在
```
COMPATIBLE_API_KEY:
```
提示下，如果尚未导出密钥，请粘贴你的密钥。
在
```
Other OpenAI-compatible endpoint model []:
```
提示下，输入模型ID，需与提供商模型目录中的显示完全一致。

例如，当你使用NVIDIA的OpenAI兼容推理端点时，输入

https://inference-api.nvidia.com

作为基础URL，并输入端点暴露的模型ID，例如

openai/openai/gpt-5.5

。

NemoClaw会发送一个真实的推理请求来验证端点和模型。如果端点没有返回OpenClaw所需的Responses API流式事件，NemoClaw会回退到聊天补全API，并将OpenClaw配置为使用

openai-completions

。

提示：

NVIDIA Nemotron模型暴露OpenAI兼容的API，因此对于任何未托管在

build.nvidia.com

上的Nemotron部署，此选项都是正确选择。常见示例包括自托管的NIM容器、企业NVIDIA AI Enterprise网关，或运行Nemotron权重的vLLM/SGLang服务器。将基础URL指向你的端点，并输入服务器报告的Nemotron模型ID，需完全一致。

选项4：Anthropic：

将推理路由到位于

https://api.anthropic.com

的Anthropic Messages API。

使用

ANTHROPIC_API_KEY

作为API密钥。可从Anthropic控制台密钥页面获取。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，输入
```
4
```
选择Anthropic。
在
```
ANTHROPIC_API_KEY:
```
提示下，如果尚未导出密钥，请粘贴你的密钥。
在
```
Choose model [1]:
```
提示下，选择一个精选模型（例如
```
claude-sonnet-4-6
```
、
```
claude-haiku-4-5
```
或
```
claude-opus-4-6
```
），或选择**Other...**输入任何Claude模型ID。

选项5：其他Anthropic兼容端点：

将推理路由到任何在

/v1/messages

实现Anthropic Messages API的服务器，包括Claude代理、Bedrock兼容网关以及自托管的Anthropic兼容服务器。

使用

COMPATIBLE_ANTHROPIC_API_KEY

作为API密钥。将其设置为你的端点所需的任何凭据。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，输入
```
5
```
选择Other Anthropic-compatible endpoint。
在
```
Anthropic-compatible base URL
```
提示下，输入代理或网关的基础URL，可从其文档中获取。
在
```
COMPATIBLE_ANTHROPIC_API_KEY:
```
提示下，如果尚未导出密钥，请粘贴你的密钥。
在
```
Other Anthropic-compatible endpoint model []:
```
提示下，输入模型ID，需与网关模型目录中的显示完全一致。

选项6：Google Gemini：

将推理路由到位于

https://generativelanguage.googleapis.com/v1beta/openai/

的Google OpenAI兼容Gemini端点。

使用

GEMINI_API_KEY

作为API密钥。可从Google AI Studio API密钥获取。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，输入
```
6
```
选择Google Gemini。
在
```
GEMINI_API_KEY:
```
提示下，如果尚未导出密钥，请粘贴你的密钥。

在

Choose model [5]:

提示下，选择一个精选模型（例如

gemini-3.1-pro-preview

、

gemini-3.1-flash-lite-preview

、

gemini-3-flash-preview

、

gemini-2.5-pro

、

gemini-2.5-flash

或

gemini-2.5-flash-lite

），或选择**Other...**输入任何Gemini模型ID。

选项7：Local Ollama：

将推理路由到本地Ollama实例。根据你的平台，向导可以使用现有守护进程、启动已安装的守护进程，或提供安装操作。

无需API密钥。在非WSL主机上，NemoClaw会生成一个令牌并启动一个经过身份验证的代理，以便容器可以访问Ollama，而无需将守护进程直接暴露到你的网络中。在WSL上，NemoClaw还可以通过

host.docker.internal

使用Windows主机上的Ollama。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，输入
```
7
```
选择Local Ollama。
在
```
Choose model [1]:
```
提示下，如果已安装Ollama模型，请从Ollama models中选择。如果未安装任何模型，请选择一个starter model立即拉取并加载，或选择**Other...**输入任何Ollama模型ID。

有关设置详情，包括GPU建议和入门模型选择，请参考使用本地推理服务器（使用

nemoclaw-user-configure-inference

技能）。

选项8：Model Router：

启动主机端模型路由器，并通过OpenShell将沙箱推理路由到该路由器。路由器会针对每个请求从

nemoclaw-blueprint/router/pool-config.yaml

中的模型池中选择模型。

使用

NVIDIA_API_KEY

作为模型池凭据。

按照以下方式响应向导：

在
```
Choose [1]:
```
提示下，输入
```
8
```
选择Model Router (experimental)。
在
```
NVIDIA_API_KEY:
```
提示下，如果尚未导出密钥，请粘贴你的密钥。
查看配置摘要并继续沙箱构建。

对于脚本化设置，请设置：

console

$ NEMOCLAW_PROVIDER=routed NVIDIA_API_KEY=<your-key> nemoclaw onboard --non-interactive

路由器在主机的

端口监听。沙箱仍会调用

https://inference.local/v1

，因此请勿将沙箱内的工具直接指向主机路由器端口。

本地NIM和本地vLLM：

Local NVIDIA NIM会在设置
```
NEMOCLAW_EXPERIMENTAL=1
```
且主机具备支持NIM的GPU时显示。NemoClaw会拉取并管理一个NIM容器。
**Local vLLM (already running)**会在NemoClaw检测到
```
localhost:8000
```
上有vLLM服务器时显示。此菜单项无需设置标志。NemoClaw会自动检测加载的模型。
**Local vLLM (managed install/start)**默认会在DGX Spark和DGX Station上显示。通用Linux NVIDIA GPU主机需要设置
```
NEMOCLAW_EXPERIMENTAL=1
```
或
```
NEMOCLAW_PROVIDER=install-vllm
```
。NemoClaw会在支持的主机上拉取并启动vLLM容器。

有关设置，请参考使用本地推理服务器（使用

nemoclaw-user-configure-inference

技能）。

Review the Configuration Before the Sandbox Build

沙箱构建前查看配置

After you enter the sandbox name, the wizard prints a review summary and asks for final confirmation before registering the provider, prompting for optional integrations, and building the sandbox image. For example, if you picked an OpenAI-compatible endpoint, the summary looks like the following:

text

  ──────────────────────────────────────────────────
  Review configuration
  ──────────────────────────────────────────────────
  Provider:      compatible-endpoint
  Model:         openai/openai/gpt-5.5
  API key:       COMPATIBLE_API_KEY (staged for OpenShell gateway registration)
  Web search:    disabled
  Messaging:     none
  Sandbox name:  my-gpt-claw
  Note:          Sandbox build typically takes 5–15 minutes on this host.
  ──────────────────────────────────────────────────
  Web search and messaging channels will be prompted next.
  Apply this configuration? [Y/n]:

The default is

, so you can press Enter once to continue. Answer

to abort cleanly, fix the entries, and re-run

nemoclaw onboard

Non-interactive runs (

NEMOCLAW_NON_INTERACTIVE=1

) print the summary for log clarity but skip the prompt.

输入沙箱名称后，向导会打印一个审核摘要，并在注册提供商、提示可选集成以及构建沙箱镜像之前请求最终确认。例如，如果你选择了OpenAI兼容端点，摘要如下所示：

text

  ──────────────────────────────────────────────────
  Review configuration
  ──────────────────────────────────────────────────
  Provider:      compatible-endpoint
  Model:         openai/openai/gpt-5.5
  API key:       COMPATIBLE_API_KEY (staged for OpenShell gateway registration)
  Web search:    disabled
  Messaging:     none
  Sandbox name:  my-gpt-claw
  Note:          Sandbox build typically takes 5–15 minutes on this host.
  ──────────────────────────────────────────────────
  Web search and messaging channels will be prompted next.
  Apply this configuration? [Y/n]:

默认选项为

，因此你可以按Enter键继续。回答

可干净地中止操作，修正输入内容后重新运行

nemoclaw onboard

。

非交互运行（

NEMOCLAW_NON_INTERACTIVE=1

）会打印摘要以便日志清晰，但会跳过提示。

Configure Web Search and Messaging

配置网页搜索和消息功能

After you confirm the summary, NemoClaw registers the selected provider with the OpenShell gateway and sets the

inference.local

route. The wizard then asks whether to enable Brave Web Search. If you enable it, enter a Brave Search API key when prompted.

The wizard also offers messaging channels such as Telegram, Discord, Slack, and WhatsApp. Press a channel number to toggle it, then press Enter to continue. If you select a channel, NemoClaw validates the token format before it bakes the channel configuration into the sandbox. For example, Slack bot tokens must start with

xoxb-

确认摘要后，NemoClaw会向OpenShell网关注册所选提供商，并设置

inference.local

路由。向导随后会询问是否启用Brave网页搜索。如果启用，请在提示时输入Brave Search API密钥。

向导还会提供消息渠道选项，如Telegram、Discord、Slack和WhatsApp。按渠道编号可切换选择，然后按Enter键继续。如果选择了某个渠道，NemoClaw会在将渠道配置嵌入沙箱之前验证令牌格式。例如，Slack机器人令牌必须以

xoxb-

开头。

Choose Network Policy Presets

选择网络策略预设

After the sandbox image builds and OpenClaw starts inside the sandbox, NemoClaw asks which network policy tier to apply. The default Balanced tier includes common development presets such as npm, PyPI, Hugging Face, Homebrew, and Brave Search when the selected agent supports web search. Use the arrow keys or

and

to move, Space to select, and Enter to confirm.

The preset selector lets you include more destinations, such as GitHub, Jira, Slack, Telegram, or local inference. Press

to toggle a selected preset between read-only and read-write when the preset supports both modes.

When the install completes, a summary confirms the running environment. Before printing the summary, NemoClaw verifies that the sandbox gateway and dashboard port forward are reachable. Inference route and messaging bridge checks are reported as warnings when they need more time or additional configuration. The

Model

and provider line reflects the inference option you picked during onboarding. The example below shows the result if you picked an OpenAI-compatible endpoint during onboarding.

text

──────────────────────────────────────────────────
NemoClaw is ready

Sandbox:  my-gpt-claw
Model:    openai/openai/gpt-5.5 (Other OpenAI-compatible endpoint)

Start chatting

  Browser:
    http://127.0.0.1:18789/

  Terminal:
    nemoclaw my-gpt-claw connect
    then run: openclaw tui

Authenticated dashboard URL, if needed:
  nemoclaw my-gpt-claw dashboard-url --quiet

Manage later

  Status:      nemoclaw my-gpt-claw status
  Logs:        nemoclaw my-gpt-claw logs --follow
  Model:       nemoclaw inference set --model <model> --provider <provider> --sandbox my-gpt-claw
  Policies:    nemoclaw my-gpt-claw policy-add
  Credentials: nemoclaw credentials reset <KEY> && nemoclaw onboard
──────────────────────────────────────────────────

[INFO]  === Installation complete ===

If you picked a different option, the

Model

line shows that provider's model and label instead. For example, you might see

gpt-5.4 (OpenAI)

claude-sonnet-4-6 (Anthropic)

gemini-2.5-flash (Google Gemini)

llama3.1:8b (Local Ollama)

nvidia-routed (Model Router)

, or

<your-model> (Other OpenAI-compatible endpoint)

沙箱镜像构建完成且OpenClaw在沙箱内启动后，NemoClaw会询问要应用哪个网络策略层级。默认的Balanced（平衡）层级包含常见的开发预设，如npm、PyPI、Hugging Face、Homebrew，以及当所选Agent支持网页搜索时的Brave Search。使用箭头键或

和

移动，按Space键选择，按Enter键确认。

预设选择器允许你添加更多目标，如GitHub、Jira、Slack、Telegram或本地推理。当预设支持两种模式时，按

可在只读和读写之间切换所选预设。

安装完成后，会显示一个摘要确认运行环境。在打印摘要之前，NemoClaw会验证沙箱网关和仪表板端口转发是否可达。当推理路由和消息桥接检查需要更多时间或额外配置时，会报告为警告。

Model

和提供商行反映了你在入门过程中选择的推理选项。以下示例显示了在入门过程中选择OpenAI兼容端点后的结果。

text

──────────────────────────────────────────────────
NemoClaw is ready

Sandbox:  my-gpt-claw
Model:    openai/openai/gpt-5.5 (Other OpenAI-compatible endpoint)

Start chatting

  Browser:
    http://127.0.0.1:18789/

  Terminal:
    nemoclaw my-gpt-claw connect
    then run: openclaw tui

Authenticated dashboard URL, if needed:
  nemoclaw my-gpt-claw dashboard-url --quiet

Manage later

  Status:      nemoclaw my-gpt-claw status
  Logs:        nemoclaw my-gpt-claw logs --follow
  Model:       nemoclaw inference set --model <model> --provider <provider> --sandbox my-gpt-claw
  Policies:    nemoclaw my-gpt-claw policy-add
  Credentials: nemoclaw credentials reset <KEY> && nemoclaw onboard
──────────────────────────────────────────────────

[INFO]  === Installation complete ===

如果你选择了其他选项，

Model

行将显示该提供商的模型和标签。例如，你可能会看到

gpt-5.4 (OpenAI)

、

claude-sonnet-4-6 (Anthropic)

、

gemini-2.5-flash (Google Gemini)

、

llama3.1:8b (Local Ollama)

、

nvidia-routed (Model Router)

或

<your-model> (Other OpenAI-compatible endpoint)

。

Run Your First Agent Prompt

运行你的首个Agent提示

You can chat with the agent from the terminal or the browser.

你可以通过终端或浏览器与Agent聊天。

Open the OpenClaw UI in a Browser to Chat with the Agent

在浏览器中打开OpenClaw UI与Agent聊天

The onboard wizard starts a background port forward to the sandbox dashboard, then prints the dashboard URL in the install summary. The default host port is

. If that port is already taken, NemoClaw uses the next free dashboard port, such as

, and prints that port in the final URL. If the chosen port becomes occupied after the sandbox build starts, onboarding rolls back the newly-created sandbox and asks you to retry instead of printing an unreachable dashboard URL. The install transcript does not print the gateway token. If the browser requires authentication, use the

dashboard-url --quiet

command to print a complete URL explicitly.

text

nemoclaw my-gpt-claw dashboard-url --quiet

Open the dashboard URL in your browser. If the browser asks for authentication, run

nemoclaw my-gpt-claw dashboard-url --quiet

and open the returned URL. Treat the authenticated URL like a password.

入门向导会启动一个后台端口转发到沙箱仪表板，然后在安装摘要中打印仪表板URL。默认主机端口为

。如果该端口已被占用，NemoClaw会使用下一个可用的仪表板端口，如

，并在最终URL中打印该端口。如果在沙箱构建开始后所选端口被占用，入门流程会回滚新创建的沙箱，并要求你重试，而不是打印无法访问的仪表板URL。安装记录不会打印网关令牌。如果浏览器需要身份验证，请使用

dashboard-url --quiet

命令显式打印完整URL。

text

nemoclaw my-gpt-claw dashboard-url --quiet

在浏览器中打开仪表板URL。如果浏览器要求身份验证，请运行

nemoclaw my-gpt-claw dashboard-url --quiet

并打开返回的URL。请像对待密码一样对待经过身份验证的URL。

Chat with the Agent from the Terminal

通过终端与Agent聊天

Connect to the sandbox and use the OpenClaw CLI.

bash

nemoclaw my-assistant connect

连接到沙箱并使用OpenClaw CLI。

bash

nemoclaw my-assistant connect

inside the sandbox:

openclaw tui

undefined

openclaw tui

undefined

References

参考资料

Load references/quickstart-hermes.md when users ask for Hermes setup, NemoHermes onboarding, or running Hermes inside OpenShell. Installs NemoClaw, selects the Hermes agent, and launches a sandboxed Hermes API endpoint.
Load references/prerequisites.md when verifying prerequisites before installation. Lists the hardware, software, and container runtime requirements for running NemoClaw.
Load references/windows-preparation.md when preparing a Windows machine for NemoClaw, enabling WSL 2, configuring Docker Desktop for Windows, or troubleshooting a Windows-specific install error. Covers Windows-only preparation steps required before the Quickstart.

当用户询问Hermes设置、NemoHermes入门或在OpenShell内运行Hermes时，加载references/quickstart-hermes.md。该文档介绍安装NemoClaw、选择Hermes Agent并启动沙箱化Hermes API端点的步骤。
在安装前验证先决条件时，加载references/prerequisites.md。该文档列出了运行NemoClaw所需的硬件、软件和容器运行时要求。
在为NemoClaw准备Windows机器、启用WSL 2、配置Windows版Docker Desktop或排查Windows特定安装错误时，加载references/windows-preparation.md。该文档涵盖了快速入门前所需的仅适用于Windows的准备步骤。

nemoclaw-user-get-started

Original

Translation

NemoClaw Quickstart with OpenClaw

基于OpenClaw的NemoClaw快速入门

Install NemoClaw and Onboard OpenClaw Agent

安装NemoClaw并入门OpenClaw Agent

Respond to the Onboard Wizard

响应入门向导

Review the Configuration Before the Sandbox Build

沙箱构建前查看配置

Configure Web Search and Messaging

配置网页搜索和消息功能

Choose Network Policy Presets

选择网络策略预设

Run Your First Agent Prompt

运行你的首个Agent提示

Open the OpenClaw UI in a Browser to Chat with the Agent

在浏览器中打开OpenClaw UI与Agent聊天

Chat with the Agent from the Terminal

通过终端与Agent聊天

inside the sandbox:

inside the sandbox:

References

参考资料

Related Skills

相关技能