The Linux Foundation has introduced an innovative approach for artificial intelligence agents to locate and communicate with one another using the existing Domain Name System infrastructure. Rather than relying on proprietary registries or having agents crawl networks and probe ports, the new DNS-AID project proposes leveraging the distributed, open DNS framework that already powers internet navigation.
DNS-AID, which stands for DNS for AI Discovery, offers a standardised method for AI agents to discover, verify, and establish communication channels without requiring any new infrastructure investment. The system enables agents and Model Context Protocol servers to utilise DNS as a global, vendor-neutral directory. This decentralised approach provides a robust alternative to the centralised registries and hardcoded URLs that currently restrict AI interoperability.
The proposal suggests that domain owners create a new well-known address that serves as a starting point for agent discovery, formatted as _index._agents.{domain}. This methodology ensures that the discovery process remains scalable, secure, and compatible with the foundational protocols of the internet. The Linux Foundation emphasises that this approach maintains the distributed nature of DNS whilst adding functionality specifically designed for AI agent communication.
Originally developed by Infoblox, DNS-AID has been positioned as an implementation-agnostic protocol that functions across any DNS provider. This characteristic is particularly significant, as it allows organisations to maintain complete control over their agent infrastructure without becoming dependent on proprietary, centralised services. The Linux Foundation is now actively inviting contributions to the DNS-AID project, encouraging the community to help refine and expand this open standard. Whilst numerous details still require development, the foundation's vision presents a compelling case for building AI agent discovery capabilities atop proven, universally accessible internet infrastructure rather than creating entirely new proprietary systems.
Fuente Original: https://news.slashdot.org/story/26/05/31/034251/ai-agents-get-their-own-directory-built-atop-dns?utm_source=rss1.0mainlinkanon&utm_medium=feed
Artículos relacionados de LaRebelión:
- AI Agents Causing Untracked Infrastructure Chaos
- Debug AI Agents Locally with Raindrops Workshop
- Anthropics AI Agents Now Learn From Mistakes
- AI Agents Microsoft Google Drive Enterprise Governance
- HUMAIN ONE Enterprise AI Agents Scale with AWS
Artículo generado mediante LaRebelionBOT
No hay comentarios:
Publicar un comentario