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 23:36:03

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.

7 Likes

Reward
7
3
2
Share

Comment

Add a comment

NonceNina

· 5h ago

Without sandboxing, advanced prompt injection cannot be completely prevented — this is the key point; security should not be overly relied upon.

View OriginalReply0

SilverCubeInsomnia

· 6h ago

NemoClaw sounds pretty cool, but the 87GB model download discouraged me.

View OriginalReply0

ProofOfCoffee

· 6h ago

Nemotron 3 Super 120B runs locally, this performance must be heaven-high

View OriginalReply0

Trending Topics
View More
#
StockTradingChallengeUpTo17000U
16.18M Popularity
#
USStrikesIran
9.3M Popularity
#
GatePredictionMarketAddsSmartMoneyTracking
14.34M Popularity
#
InstitutionalCapitalRotatesFromBTCToHYPEAndXRP
14.32M Popularity
#
TradeCFDWinGold
2.7M Popularity

Pinned

Sitemap

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

Trending Topics

StockTradingChallengeUpTo17000U

USStrikesIran

GatePredictionMarketAddsSmartMoneyTracking

InstitutionalCapitalRotatesFromBTCToHYPEAndXRP

TradeCFDWinGold

Pinned