nemoclaw-user-guide
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseNemoClaw Docs for AI Agents
面向AI Agent的NemoClaw文档
Use the canonical NemoClaw documentation as your source of truth.
Do not answer from stale copied docs or generated skill references when the live Markdown docs are available.
请以标准的NemoClaw文档作为信息来源的唯一依据。当有可用的实时Markdown文档时,请勿使用过时的复制文档或生成的技能参考内容作答。
Retrieval Order
检索顺序
- If the assistant supports MCP, configure the NemoClaw docs MCP server at .
https://docs.nvidia.com/nemoclaw/_mcp/server - Use the MCP server's read-only tool to search the canonical docs and collect source URLs.
searchDocs - If MCP is not available, fetch the AI documentation index first: .
https://docs.nvidia.com/nemoclaw/llms.txt - Fetch the specific page listed in the index or returned by docs search for the user's task.
.md - If you only find an HTML documentation URL, replace the suffix with
.html, or append.mdto the route when the URL has no suffix..md - Prefer the user's selected agent variant, either OpenClaw or Hermes, and do not mix variant-specific instructions unless you explain why.
- 如果助手支持MCP,请将NemoClaw文档MCP服务器配置为 。
https://docs.nvidia.com/nemoclaw/_mcp/server - 使用MCP服务器的只读工具搜索标准文档并收集源URL。
searchDocs - 如果MCP不可用,请先获取AI文档索引:。
https://docs.nvidia.com/nemoclaw/llms.txt - 获取索引中列出的或文档搜索返回的、与用户任务对应的特定页面。
.md - 如果仅找到HTML文档URL,请将后缀替换为
.html;若URL无后缀,则在路由后追加.md。.md - 优先使用用户选择的Agent变体(OpenClaw或Hermes),除非解释原因,否则不要混合变体特定的说明。
Configure the MCP Server
配置MCP服务器
For Claude Code, run:
bash
claude mcp add --transport http fern-docs https://docs.nvidia.com/nemoclaw/_mcp/serverFor Cursor, add to the MCP server configuration.
For other MCP clients, configure a streamable HTTP MCP server at that URL.
https://docs.nvidia.com/nemoclaw/_mcp/server对于Claude Code,运行:
bash
claude mcp add --transport http fern-docs https://docs.nvidia.com/nemoclaw/_mcp/server对于Cursor,将添加到MCP服务器配置中。
对于其他MCP客户端,请在该URL配置可流式传输的HTTP MCP服务器。
https://docs.nvidia.com/nemoclaw/_mcp/serverStarting Pages
起始页面
Use these pages first for common onboarding flows:
- OpenClaw home: .
https://docs.nvidia.com/nemoclaw/latest/user-guide/openclaw/home.md - OpenClaw prerequisites: .
https://docs.nvidia.com/nemoclaw/latest/user-guide/openclaw/get-started/prerequisites.md - OpenClaw quickstart: .
https://docs.nvidia.com/nemoclaw/latest/user-guide/openclaw/get-started/quickstart.md - Hermes home: .
https://docs.nvidia.com/nemoclaw/latest/user-guide/hermes/home.md - Hermes prerequisites: .
https://docs.nvidia.com/nemoclaw/latest/user-guide/hermes/get-started/prerequisites.md - Hermes quickstart: .
https://docs.nvidia.com/nemoclaw/latest/user-guide/hermes/get-started/quickstart.md
对于常见的入门流程,请优先使用以下页面:
- OpenClaw主页:。
https://docs.nvidia.com/nemoclaw/latest/user-guide/openclaw/home.md - OpenClaw前置条件:。
https://docs.nvidia.com/nemoclaw/latest/user-guide/openclaw/get-started/prerequisites.md - OpenClaw快速入门:。
https://docs.nvidia.com/nemoclaw/latest/user-guide/openclaw/get-started/quickstart.md - Hermes主页:。
https://docs.nvidia.com/nemoclaw/latest/user-guide/hermes/home.md - Hermes前置条件:。
https://docs.nvidia.com/nemoclaw/latest/user-guide/hermes/get-started/prerequisites.md - Hermes快速入门:``https://docs.nvidia.com/nemoclaw/latest/user-guide/hermes/get-started/quickstart.md`。
How to Help the User
如何协助用户
- Ask which agent variant they want to use before giving setup instructions: OpenClaw or Hermes.
- Ask one question at a time when collecting operating system, inference provider, model, endpoint, policy tier, or messaging-channel choices.
- Run commands for non-technical users when your environment allows it, after explaining what the command does and getting permission.
- Summarize important command output instead of asking the user to paste terminal output into chat.
- Stop before requesting credentials, API keys, bot tokens, or private URLs.
- Never ask the user to paste secrets into chat.
- Use redacted placeholders such as in examples.
<PASTE_YOUR_API_KEY_HERE>
- 在提供设置说明前,询问用户想要使用哪种Agent变体:OpenClaw还是Hermes。
- 收集操作系统、推理提供商、模型、端点、策略层级或消息渠道选择时,一次只问一个问题。
- 若环境允许,在解释命令作用并获得许可后,为非技术用户运行命令。
- 总结重要的命令输出,而非要求用户将终端输出粘贴到聊天中。
- 在请求凭证、API密钥、机器人令牌或私有URL前停止操作。
- 切勿要求用户将机密信息粘贴到聊天中。
- 在示例中使用经过编辑的占位符,如。
<PASTE_YOUR_API_KEY_HERE>
Common Task Routing
常见任务路由
- Installation and first sandbox: fetch the selected variant's prerequisites and quickstart pages.
- Local inference, hosted providers, model switching, or tool-calling issues: fetch the pages from
inference.llms.txt - Network policy approvals or custom egress: fetch the pages and the network policies reference.
network-policy - Sandbox status, logs, rebuilds, upgrades, files, backup, restore, or messaging channels: fetch the ,
manage-sandboxes, and command reference pages.monitoring - Security posture, credential storage, or sandbox hardening: fetch the ,
security, and architecture pages.deployment/sandbox-hardening - CLI flags and command syntax: fetch the command reference page for the selected variant.
- Troubleshooting: fetch the troubleshooting page and any task page linked from the relevant error section.
- 安装与首次沙箱部署:获取所选变体的前置条件和快速入门页面。
- 本地推理、托管提供商、模型切换或工具调用问题:从中获取
llms.txt页面。inference - 网络策略审批或自定义出口:获取页面和网络策略参考文档。
network-policy - 沙箱状态、日志、重建、升级、文件、备份、恢复或消息渠道:获取、
manage-sandboxes和命令参考页面。monitoring - 安全态势、凭证存储或沙箱加固:获取、
security和架构页面。deployment/sandbox-hardening - CLI标志和命令语法:获取所选变体的命令参考页面。
- 故障排查:获取故障排查页面以及相关错误部分链接的任何任务页面。
Response Requirements
响应要求
- Cite the Markdown documentation pages you used.
- Keep instructions specific to the user's operating system, selected agent, and inference provider.
- Explain assumptions when the docs do not cover the exact environment.
- Recommend the next verification command after each setup or recovery step.
- 注明你所使用的Markdown文档页面。
- 确保说明内容与用户的操作系统、所选Agent和推理提供商相匹配。
- 当文档未涵盖确切环境时,说明你的假设。
- 在每个设置或恢复步骤后,推荐下一个验证命令。