AI Compare
​
​
ToolsArticlesServices
Best for
    All tools

    Sales

    AI tools for finding leads, qualifying them, preparing quotes, following up and keeping the CRM up to date.

    Marketing

    AI tools for content, social media, images, video, SEO and campaigns.

    Customer service

    AI tools for answering customer emails, chats and calls, handling requests and escalating the hard cases.

    Operations

    AI tools for running the daily work: workflows, scheduling, projects, purchasing and delivery.

    Finance

    AI tools for invoices, bookkeeping, reconciliation, spreadsheets and financial reporting.

    Management & Admin

    AI tools for owners, managers and office staff: planning, reports, documents, meetings, scheduling and everyday admin.

    HR

    AI tools for hiring, screening candidates, onboarding, training and answering employee questions.

    Legal & Compliance

    AI tools for reviewing contracts, tracking deadlines and preparing compliance work for a qualified person to check.

    IT & Development

    AI tools for developers and IT teams: coding, AI models, agents, infrastructure and integrations.

Find AI tools for your team
AllAssistantsWriting & DocsImagesVideoAudioAI AgentsAutomationCode
← Back to tools

•

2026-03-15

NemoClaw logo

NemoClaw

Not rated yet

22K GitHub stars

Type:

Tool

Platforms:

Github

Task:

Chat with AIRun AI agentsEngineer promptsMonitor infrastructureWrite code

Best for:

IT & Development
Visit websiteView on GitHub

Pricing


Pricing information has not been added yet.

Overview

NemoClaw is an NVIDIA open-source project for building and operating AI agents with an emphasis on enterprise-ready infrastructure and accelerated AI components. It brings together agent runtime concepts with NVIDIA's model, inference, and platform ecosystem to support more controlled deployment of agentic applications.

The repository documents how agents can be configured, connected to tools and services, and run within infrastructure designed for production concerns such as security, observability, scalable inference, and managed execution. It is intended to complement the broader NVIDIA AI stack rather than function only as a standalone prompt library.

NemoClaw is most relevant to developers and organizations already using NVIDIA infrastructure who want to extend that environment into agent applications. It provides patterns and components for moving agent workloads from experimentation toward systems that can be deployed and operated within enterprise environments.

README

NVIDIA NemoClaw: Reference Stack for Sandboxed AI Agents in OpenShell

License Security Policy Discord

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, snapshots, 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.

AgentGuide
OpenClaw (default)Quickstart with OpenClaw
HermesQuickstart with Hermes
LangChain Deep Agents CodeQuickstart with LangChain Deep Agents Code

Documentation

Refer to the following pages on the official documentation website for more information on NemoClaw.

PageDescription
OverviewWhat NemoClaw does and how it fits together.
Architecture OverviewHigh-level overview of the host CLI, agent integration layer, blueprint, sandbox lifecycle, and protection layers.
EcosystemHow OpenClaw, OpenShell, and NemoClaw form a stack and when to use NemoClaw versus OpenShell alone.
Architecture DetailsDetailed description of agent integration structure, blueprint lifecycle, sandbox environment, and host-side state.
PrerequisitesHardware, software, and supported platforms, with any platform-specific pre-setup.
Choose an Inference ProviderSupported providers, validation, and routed inference configuration.
Network PoliciesBaseline rules, operator approval flow, and egress control.
Customize Network PolicyStatic and dynamic policy changes, presets.
Security Best PracticesControls reference, risk framework, and posture profiles for sandbox security.
Sandbox HardeningContainer security measures, capability drops, process limits.
CLI CommandsFull NemoClaw CLI command reference.
TroubleshootingCommon 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.

NeedChannel
Setup or usage questionsGitHub Discussions or Discord
Reproducible bugsGitHub Issues
Feature proposalsStart with GitHub Discussions, then open an issue when the scope is clear
Current prioritiesCurrent Priorities
Contribution helpCONTRIBUTING.md
Security vulnerabilitiesUse 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 psirt@nvidia.com 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.

Releases

Release information has not been added yet.

Complete your AI stack

Add a general assistant, research, coding, monitoring, and team productivity to your automations.

ChatGPT logo
ChatGPT
General assistant

General-purpose AI assistant for research, writing, coding, data analysis, image creation, and everyday productivity

View tool
Perplexity logo
Perplexity
Research

AI-powered search and research assistant

View tool
Cursor logo
Cursor
Build integrations

AI coding editor and autonomous software development platform

View tool
Best alternatives

Compare similar tools in the same category.

CodeRabbit logo

CodeRabbit

AI-powered code review assistant for pull requests.

OpenClaw logo

OpenClaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Cursor logo

Cursor

AI coding editor and autonomous software development platform

DeepSeek logo

DeepSeek

AI assistant for reasoning, coding, research, and agent tasks

ECC logo

ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

View all in this category
Help
Pick an answer below
Hi! I can point you to the right tool or guide. What are you looking for?
Browse all articles