Urgent.News

What's breaking now, across thousands of outlets.

AI

Manage agents, tools and skills at scale with AWS Agent Registry

AWS Agent Registry is now generally available: a single, searchable, governed catalog for the agents, tools, skills, and custom resources across your organization. This post explains what Registry is and walks through its publishing, curation, and discovery workflows, plus enterprise considerations and what's next.

Managing agents, tools, and skills at scale can be challenging for organizations. Teams often build in isolation without a shared record of what exists, who owns it, or whether it's been reviewed. This has shifted the focus from building agents and tools to discovering and governing them. AWS Agent Registry addresses these challenges by providing a single, searchable, governed catalog for agents, tools, skills, and custom resources within an organization's environment.

The Registry offers three key benefits for enterprises:

1. No authoritative inventory: Without a central registry, there's no single record of existing agents and tools, leading to duplicative effort, version drift, and scattered capabilities. AWS Agent Registry resolves this by offering a comprehensive and searchable catalog of all registered resources.

2. No cross-team discovery: When valuable tools, agents, and skills exist, they remain unused due to lack of discoverability. The Registry's Discovery Plane provides a curated view of only the resources that have passed the organization's approval bar, enabling developers and consumers to find the resources they need quickly and efficiently.

3. No governance or audit trail: Without a centralized registry, there's no way to track access, security reviews, and failure tracing. AWS Agent Registry ensures governance and audit trails by assigning owners, maintaining clear lineages, and providing trust signals about resources.

Registry supports four record types: Model Context Protocol (MCP) server, its tools, resources, and prompts; Agent2Agent (A2A) agent cards defining agents and their skills; agent skill definitions in markdown files and associated code/packages; and a custom descriptor that must be valid JSON.

The Registry operates through two complementary planes: the Governance Plane and the Discovery Plane. The Governance Plane is the authoritative store for resources within a defined scope, where admins configure rules for management, such as compliance and security signals, discovery policies, and custom metadata schemas. The Discovery Plane is what consumers interact with daily, presenting a curated, high-performance view of only the resources that have passed the organization's approval bar.

It supports semantic and lexical searches, providing summarized compliance and security indicators to aid decision-making without overwhelming the users with governance details.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at aws.amazon.com →

More in AI

Instagram puts new limits on undisclosed AI profiles

As frustration over AI influencers has been growing, Instagram is limiting the reach of undisclosed AI profiles.

  • Instagram will rename AI creator label to AI-generated profile.
  • Creators without proper disclosure face reduced reach.
  • Label targets AI-generated profiles, not AI editing tools.

OpenAI Cuts Off Cursor’s Model Access After SpaceX Acquisition

OpenAI is ending Cursor’s direct access to its AI models after Elon Musk’s SpaceX acquired its parent company, Anysphere. This is the next move in the increasingly bitter conflict between Elon Musk and the company he helped found. Just because you’re filthy rich doesn’t mean you still can’t have petty fights. In the latest example […]

Why some AI ads fail while others succeed

Artificial intelligence can create realistic depictions of just about anything, but that does not mean advertisers should lean on the technology, according to a study led by University of Mississippi professors.

New AI method can support real-time management of infectious diseases

For the past 25 years, one discipline has been revolutionizing epidemiology: phylodynamics. By using genetic sequences, scientists can study how pathogens evolve. Thanks to mathematics, these data can be coherently organized into phylogenetic trees, with each branch representing a chain of transmission and each leaf representing an…

More from Monday 31 August →