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, which are expected 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 defend against advanced prompt injection; testing should be conducted on isolated systems.

MeNews

2026-05-25 06:03:48

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. The active operation time is estimated at 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)

NVDA-0.31%

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.

9 Likes

Reward
9
7
Repost
Share

Comment

Add a comment

0XsundayCook

· 11h ago

The Telegram bot token design is good; you can access your AI anytime and anywhere.

View OriginalReply0

TheFeelingOfEthInTheSeaBreeze

· 11h ago

The isolation system testing is a very important suggestion; don't mess around on the main machine.

View OriginalReply0

LiquidityTeaMaster

· 11h ago

NemoClaw is a pretty interesting name; the combination of OpenShell + OpenClaw sounds very hardcore.

View OriginalReply0

Yield慢炖锅

· 11h ago

Open-source stack + detailed tutorial, a treasure for users looking to break free from cloud services

View OriginalReply0

NFTeaTime

· 11h ago

Nemotron 3 Super 120B runs locally; privacy is indeed much stronger than in the cloud.

View OriginalReply0

BluePeonyDarkroom

· 11h ago

Deploying in 20-30 minutes is considered fast, but the time for downloading the model is separate and needs to be planned in advance.

View OriginalReply0

ForkliftTrader

· 11h ago

Ubuntu 24.04 + Docker 28.x, the environment requirements are quite new; older machines may need to upgrade first.

View OriginalReply0

Trending Topics
View More
#
StockTradingChallengeUpTo17000U
15.93M Popularity
#
USIranDraftDeal
289.22K Popularity
#
TradeCFDWinGold
3.03M Popularity
#
HYPEMarketCapSurpassesDOGE
12.64M Popularity
#
PlatinumCardCreatorExclusive
155.8K Popularity

Pinned

Sitemap

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

Trending Topics

StockTradingChallengeUpTo17000U

USIranDraftDeal

TradeCFDWinGold

HYPEMarketCapSurpassesDOGE

PlatinumCardCreatorExclusive

Pinned