安装前需先查看官方 Prerequisites 文档确认平台与依赖;快速安装默认只装 OpenClaw,要用 Hermes 或 LangChain Deep Agents Code 需在提示处输入 n 交互选择;项目处于 alpha 阶段,维护者按尽力而为处理 issue,无保证响应时间。
NemoClaw
NVIDIAApache-2.0活跃维护在 NVIDIA OpenShell 沙箱里安全运行 Hermes、LangChain Deep Agents、OpenClaw 等智能体,并统一托管推理调用,解决智能体执行环境隔离与模型接入管理问题。
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
在受支持的 DGX 或 WSL 主机上运行安装器,在 `Run express install with these settings? [Y/n]:` 提示处按回车即用推荐预设(默认安装 OpenClaw);贡献者可用 `./scripts/dev-setup.sh` 准备源码环境。README 未说明具体显存或 GPU 型号,仅提到需在受支持的 DGX 或 WSL 主机上安装,详细硬件与平台要求见官方 Prerequisites 文档。
在 NVIDIA OpenShell 沙箱里安全运行 OpenClaw、Hermes 等 AI Agent 的参考栈
在 NVIDIA OpenShell 沙箱里安全运行 Hermes、LangChain Deep Agents、OpenClaw 等智能体,并统一托管推理调用,解决智能体执行环境隔离与模型接入管理问题。
核心能力
- 通过 OpenShell 沙箱隔离运行受支持的 AI Agent
- 提供引导式安装向导与托管推理配置
- 用网络策略控制沙箱出站访问与审批流
- 由 OpenShell 支撑沙箱状态持久化与生命周期操作
- 提供 NemoClaw CLI 及各 Agent 专属别名命令
容易踩的坑
- ci-native-podman-e2e-2026-10-01Native Podman E2E toolchains — 2026-10-01pre-release最新正式版2026-10-01 · 2026-10-01 08:06 UTC
Pinned CI toolchains for NemoClaw's native Podman E2E jobs. These assets preserve existing reviewed binaries so E2E startup no longer depends on expiring GitHub Actions artifacts.
Recovered without modification from trusted main E2E run 36537895087, generate-matrix job 109331743180, at commit 2272c5c15dd873c79436120ac0bfd21f70ae962e. That job staged the original toolchains through action 8d7409d66a0e664829f9ddab177aa8460974291f before candidate checkout, verifying source run 33211526093 and its artifact identities. The original source artifacts have since expired.
Architecture Retained artifact ID Exact ZIP SHA-256 AMD64 11019217721 2a07674b09da33f24772936e5fc3e8d7e80dbbe096cc70e9fa32babc9177a006 ARM64 11019212869 dba39bc41923592bef67980e4d179c8b6d8442a6157e67621e53abf969072e3a Each archive contains its source-revision manifest and SHA256SUMS. Both archive digests and every listed file checksum were verified before staging these assets. Components remain Podman 6.1.0, Netavark 2.1.0, Aardvark DNS 2.1.0, and pasta 2026_07_28.f8df3f1. No binaries were rebuilt or executed during recovery.
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
NVIDIA NemoClaw: Reference Stack for Sandboxed AI Agents in OpenShell
NVIDIA NemoClaw is an open source reference stack for running supported AI agents more safely inside NVIDIA OpenShell sandboxes. It provides guided onboarding, managed inference, network policy, managed integrations, OpenShell-backed state persistence, and lifecycle operations through the NemoClaw CLI and its agent-specific aliases.
Supported agents:
- OpenClaw (default)
- Hermes
- LangChain Deep Agents Code
For capabilities, architecture, security controls, and the full feature list, see the NemoClaw documentation.
Get Started
Start with Your Coding Agent
Use the starter prompt when you want Cursor, Claude Code, Codex, Copilot, or another local coding agent to install NemoClaw with you.
Copy the NemoClaw starter prompt.
The prompt tells your agent to use NemoClaw docs and skills, ask one question at a time, run commands only with your approval, and keep secrets out of chat.
Install Using the Installer in Your Terminal
Review Prerequisites before installing.
On a supported DGX or Windows Subsystem for Linux (WSL) host, press Enter at the Run express install with these settings? [Y/n]: prompt to use the recommended preset settings for that platform.
Express install mode installs OpenClaw by default.
If you accept, refer to NemoClaw Quickstart with OpenClaw.
Enter n if you want to choose Hermes or LangChain Deep Agents Code, a sandbox name, an inference provider, and a model interactively.
When connecting to a Hermes sandbox from a light terminal, NemoClaw may install a managed nemoclaw-light Hermes skin for readable assistant text; it removes that managed skin state again when the terminal no longer needs it and preserves any user-selected Hermes skin.
| Agent | Guide |
|---|---|
| OpenClaw (default) | Quickstart with OpenClaw |
| Hermes | Quickstart with Hermes |
| LangChain Deep Agents Code | Quickstart with LangChain Deep Agents Code |
Documentation
Refer to the following pages on the official documentation website for more information on NemoClaw.
| Page | Description |
|---|---|
| Overview | What NemoClaw does and how it fits together. |
| Architecture Overview | High-level overview of the host CLI, agent integration layer, blueprint, sandbox lifecycle, and protection layers. |
| Ecosystem | How OpenClaw, OpenShell, and NemoClaw form a stack and when to use NemoClaw versus OpenShell alone. |
| Architecture Details | Detailed description of agent integration structure, blueprint lifecycle, sandbox environment, and host-side state. |
| Prerequisites | Hardware, software, and supported platforms, with any platform-specific pre-setup. |
| Choose an Inference Provider | Supported providers, validation, and routed inference configuration. |
| Network Policies | Baseline rules, operator approval flow, and egress control. |
| Customize Network Policy | Static and dynamic policy changes, presets. |
| Security Best Practices | Controls reference, risk framework, and posture profiles for sandbox security. |
| Sandbox Hardening | Container security measures, capability drops, process limits. |
| CLI Commands | Full NemoClaw CLI command reference. |
| Troubleshooting | Common issues and resolution steps. |
Community
Join the NemoClaw community to ask questions, share feedback, and report issues. NemoClaw is an alpha project, so maintainers review issues, discussions, and pull requests on a best effort basis without guaranteed response timelines.
| Need | Channel |
|---|---|
| Setup or usage questions | GitHub Discussions or Discord |
| Reproducible bugs | GitHub Issues |
| Feature proposals | Start with GitHub Discussions, then open an issue when the scope is clear |
| Examples | Community Examples · Contribute an example |
| Current priorities | Current Priorities |
| Contribution help | CONTRIBUTING.md |
| Security vulnerabilities | Use the private channels in SECURITY.md; do not open public issues |
Contributing
We welcome contributions. See CONTRIBUTING.md for development setup, coding standards, and the PR process.
Prepare a source checkout without creating a runtime sandbox:
./scripts/dev-setup.sh
Or ask a compatible coding agent to use the repository's contributor-onboarding skill:
Set up this machine as a NemoClaw contributor and prepare it for a first PR.
The contributor path is separate from the end-user installer above.
The default and --repair modes change only repository-local dependencies, builds, and hooks.
Use ./scripts/dev-setup.sh --expose-cli only when you explicitly want a host-visible development CLI.
Use ./scripts/dev-setup.sh --with-runtime only when your change needs sandbox validation; that approved flow also opts into CLI exposure.
Security
NVIDIA takes security seriously. If you discover a vulnerability in NemoClaw, DO NOT open a public issue. Use one of the private reporting channels described in SECURITY.md:
- Submit a report through the NVIDIA Vulnerability Disclosure Program.
- Send an email to [email protected] encrypted with the NVIDIA PGP key.
- Use GitHub's private vulnerability reporting to submit a report directly on this repository.
For security bulletins and PSIRT policies, visit the NVIDIA Product Security portal.
Current Priorities
NemoClaw's current priorities are maintained here as a public orientation point for contributors and community members. This list is not a delivery commitment, support promise, or fixed roadmap; priorities can change as maintainers respond to security, quality, platform readiness, and community feedback.
- Improve install and onboarding reliability across tested platforms.
- Strengthen sandbox hardening, credential handling, and network-policy defaults.
- Validate local and routed inference behavior for supported provider paths.
- Keep documentation, troubleshooting guidance, and agent skills aligned with supported workflows.
For specific scoped work, use GitHub Issues and start broader proposals in GitHub Discussions. Security vulnerabilities must use the private reporting channels in SECURITY.md, not public issues.
Notice and Disclaimer
This software automatically retrieves, accesses or interacts with external materials. Those retrieved materials are not distributed with this software and are governed solely by separate terms, conditions and licenses. You are solely responsible for finding, reviewing and complying with all applicable terms, conditions, and licenses, and for verifying the security, integrity and suitability of any retrieved materials for your specific use case. This software is provided "AS IS", without warranty of any kind. The author makes no representations or warranties regarding any retrieved materials, and assumes no liability for any losses, damages, liabilities or legal consequences from your use or inability to use this software or any retrieved materials. Use this software and the retrieved materials at your own risk.
License
Apache 2.0. See LICENSE.