The tutorial is based on the open-source NemoClaw stack, integrating OpenShell and OpenClaw, providing a solution for long-term, secure deployment of autonomous AI assistants locally. Using the NVIDIA DGX Spark system as an example, it details environment requirements (Ubuntu 24.04, Docker 28.x, Ollama, Telegram bot token, etc.) and deployment steps, estimated to take 20–30 minutes, with an additional 15–30 minutes to download approximately 87GB of models. The core components include NemoClaw, OpenShell, OpenClaw, Nemotron 3 Super 120B, and NIM/Ollama inference deployment. The article notes that although there is strong isolation, no sandbox can fully prevent advanced prompt injection; testing should be conducted on isolated systems.

MeNews

2026-05-25 04:30:33

Abstract generation in progress

ME News Report, April 18 (UTC+8), NVIDIA recently released a technical tutorial guiding developers on how to build a secure, long-running, fully local autonomous AI assistant. The tutorial is based on NVIDIA's open-source reference stack NemoClaw, which integrates OpenShell secure runtime and OpenClaw self-hosted gateway, aiming to address data privacy and control risks when deploying AI agents on third-party clouds. The tutorial provides detailed deployment steps on NVIDIA DGX Spark (GB10) systems, including environment setup, local service models, installation stack, and connection to Telegram. Deployment requires meeting specific hardware (DGX Spark running Ubuntu 24.04 LTS), software (Docker 28.x+, Ollama), and prerequisites such as creating a Telegram bot token. Estimated active operation time is 20-30 minutes, plus an initial model download of about 87 GB taking 15-30 minutes. Core components include NemoClaw, OpenShell, OpenClaw, Nemotron 3 Super 120B LLM, and inference deployment with NIM or Ollama. The article also notes that while OpenShell offers strong isolation features, no sandbox can provide complete protection against advanced prompt injections, and it is recommended to deploy new tools on isolated systems during testing. (Source: InFoQ)

View Original

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.

11 Likes

Reward
11
6
1
Share

Comment

Add a comment

TreatEarningsAsSnacks

· 4h ago

OpenShell+OpenClaw this combo name is a bit edgy, but the tech stack looks solid.

View OriginalReply0

ChaintraceAuntie

· 6h ago

Nemotron 3 Super 120B runs locally, finally no longer having to worry about API quota limits

View OriginalReply0

PixelPnl

· 6h ago

Long-term deployment plan + strong isolation design, this set is suitable for teams with high privacy requirements

View OriginalReply0

GateUser-4bd1cc87

· 6h ago

Be careful when setting the Telegram Bot token to avoid common pitfalls, and remember not to upload the .env file to GitHub.

View OriginalReply0

LeverageWithdrawalInProgress

· 6h ago

The prompt injection warning is very well written; without a sandbox, it's perfect, and security awareness is in place.

View OriginalReply0

ForkInTheRoadmap

· 6h ago

NVIDIA DGX Spark runs 120B, this configuration threshold is a bit high, ordinary players can only watch.

View OriginalReply0

Trending Topics
View More
#
StockTradingChallengeUpTo17000U
16.16M Popularity
#
USIranDraftDeal
283.46K Popularity
#
TradeCFDWinGold
3.02M Popularity
#
HYPEMarketCapSurpassesDOGE
12.64M Popularity
#
PlatinumCardCreatorExclusive
153.97K Popularity

Pinned

Sitemap

NVIDIA releases tutorial on building a local sandboxed AI assistant based on NemoClaw

Trending Topics

StockTradingChallengeUpTo17000U

USIranDraftDeal

TradeCFDWinGold

HYPEMarketCapSurpassesDOGE

PlatinumCardCreatorExclusive

Pinned