Skip to main content
← Back to feed
Official announcementNVIDIA Developer Blog

Build Specialized Agents on a Stack You Control with NVIDIA NemoClaw

Build Specialized Agents on a Stack You Control with NVIDIA NemoClaw

From the official release

Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces policies, along with optimization and observability tools for reliable execution.

For production agents, the challenge lies in making these agents capable and safe to operate with access to real enterprise systems and data.

This post explains how these components work together, with a focus on how NVIDIA NemoClaw open blueprints enable developers to build specialized agents on a stack they can own, customize, and run. This post provides criteria to help developers integrate NemoClaw with a harness they already use: OpenClaw, Hermes Agent, or LangChain Deep Agents.

What an agent harness provides[](#what_an_agent_harness_provides)

An agent requires four things:

  • A model that reasons.

This is a short excerpt. Read the full announcement on the official source.

Continue on developer.nvidia.com → (opens in a new window)
Amazon Bedrock expands API support and introduces Cross Region Inferencing for OpenAI models in AWS GovCloud (US)
Official announcement

Amazon Bedrock expands API support and introduces Cross Region Inferencing for OpenAI models in AWS GovCloud (US)

AWS What’s New

Amazon Bedrock now supports the OpenAI GPT-5.6 models (Terra and Luna) on the bedrock-runtime endpoint, with support for the Responses, Converse, and Chat Completions APIs in AWS GovCloud (US). It also adds support for cross-Region inference, allowing customers to use cross-Regio

Run AI Models for Edge Application Development with Just a Few Commands
Official announcement

Run AI Models for Edge Application Development with Just a Few Commands

NVIDIA Developer Blog

AI is expanding beyond the data center as developers build a new generation of agents to act at the edge: monitoring driver attention and cabin conditions,... AI is expanding beyond the data center as developers build a new generation of agents to act at the edge: monitoring driv

Google Fitbit Edge: On shelves now
Official announcement

Google Fitbit Edge: On shelves now

Google Fitbit Blog

Shop the new Google Fitbit Edge featuring a bright, large display and physical side buttons for easy control. Upgrade your fitness tracker today.

Web Search now available on Kiro in AWS GovCloud (US)
Official announcement

Web Search now available on Kiro in AWS GovCloud (US)

AWS What’s New

Kiro web search gives the agent real-time access to current information on the internet, so its answers draw on up-to-date search results and page content. The agent uses web search automatically when a question involves recent changes or topics beyond the model's training data.

Wealth Management Client Onboarding Needs More Than AI
Official announcement

Wealth Management Client Onboarding Needs More Than AI

Databricks Blog

Wealth Management client onboarding can stall even when every system has done its job. The document is collected...

Amazon Connect Customer automatically saves in-progress emails as drafts
Official announcement

Amazon Connect Customer automatically saves in-progress emails as drafts

AWS What’s New

Amazon Connect Customer automatically saves in-progress emails as drafts, helping agents resume work without losing progress when connectivity is interrupted or when their browser is accidentally closed or refreshed. When agents return, their drafts are restored with the message