Want AI agents to work together? The Linux Foundation has a plan

The rise of AI agents, programs designed to perform tasks autonomously without explicit step-by-step instructions, presents a significant challenge in interoperability: how can these disparate AI agents effectively work together? Cisco's AGNTCY (pronounced "agency") project offers a solution to this critical challenge. Donated to the Linux Foundation and supported by industry leaders such as Dell, Google Cloud, Oracle, and Red Hat, AGNTCY aims to establish an open-standard infrastructure, conceptualized as the "Internet of Agents." This framework is designed to enable AI agents from various vendors and platforms to communicate and collaborate seamlessly. Without a standardized approach, AI agents risk becoming isolated silos, which would limit their overall utility. History has shown that technological advancements flourish when common standards emerge, much like TCP/IP did for the internet or 802.11 for Wi-Fi. AGNTCY aspires to be that foundational standard for agentic AI. Vijoy Pandey, GM and SVP of Outshift by Cisco, stressed the importance of community ownership over vendor control, stating, "The missing piece isn't smarter agents — it's complete infrastructure that lets any agent work with any other agent, regardless of who built it or where it runs."

Core Components of AGNTCY

The project provides a comprehensive framework to address the complexities of multi-agent collaboration:

• Agent Discovery: The Open Agent Schema Framework (OASF) functions like a "DNS for agents," facilitating their ability to find and understand each other's capabilities.
• Agent Identity: Verifiable identities, secured through cryptography, ensure agents can prove their authenticity and perform authorized actions across organizations securely.
• Agent Messaging: The Secure Low-latency Interactive Messaging (SLIM) protocol supports sophisticated, multi-modal communication patterns, including human-in-the-loop interactions and quantum-safe security.
• Agent Observability: A specialized monitoring framework offers visibility into multi-agent workflows, which is crucial for debugging probabilistic AI systems.
Jim Zemlin, the Linux Foundation’s executive director, highlighted the significance of open, neutral infrastructure: "The AGNTCY project lays groundwork for secure, interoperable collaboration among autonomous agents. We are pleased to welcome the AGNTCY project… to ensure its infrastructure remains open, neutral, and community-driven."

Interoperability with Other AI Protocols

AGNTCY is designed to complement other emerging AI agency standards, such as the Agent2Agent (A2A) protocol and Anthropic's Model Context Protocol (MCP), both of which have recently been contributed to the Linux Foundation. AGNTCY enables agents using these protocols to discover each other, communicate securely via SLIM, and monitor interactions through its observability SDKs.

Industry Support and Future Outlook

John Roese, Dell Technologies’ global CTO and chief AI officer, commented, "Interoperability is central to Dell's agentic AI vision. Interworking technologies must accommodate agents wherever they are deployed, whether in public clouds, private data centers, the edge, or on devices." Under the stewardship of the Linux Foundation, AGNTCY's working groups are continuing development with broad community participation to accelerate adoption. The project's code and documentation are publicly accessible on GitHub for developers and contributors.

---

Originally published at ZDNet on July 29, 2025

---

Frequently Asked Questions (FAQ)

What are AI agents? AI agents are programs designed to perform tasks autonomously, without needing explicit step-by-step instructions from a human. What is the main challenge with AI agents? The primary challenge is interoperability – enabling different AI agents, potentially from various vendors and platforms, to communicate and collaborate effectively. What is Cisco's AGNTCY project? AGNTCY is a project initiated by Cisco, now donated to the Linux Foundation, aiming to build an open-standard infrastructure called the "Internet of Agents" to solve AI agent interoperability issues. Who supports the AGNTCY project? Key industry leaders such as Dell, Google Cloud, Oracle, and Red Hat support the AGNTCY project. What are the core components of AGNTCY? The core components are Agent Discovery (Open Agent Schema Framework), Agent Identity (cryptographically verifiable), Agent Messaging (SLIM protocol), and Agent Observability (monitoring framework). How does AGNTCY relate to other AI agency standards? AGNTCY complements other standards like the Agent2Agent (A2A) protocol and Anthropic's Model Context Protocol (MCP), enabling seamless communication and collaboration between agents using these different protocols. Where can I find the AGNTCY project's resources? The project's code and documentation are publicly available on GitHub.

Crypto Market AI's Take

The development of a standardized infrastructure like Cisco's AGNTCY project is crucial for the future of AI collaboration. In the rapidly evolving landscape of artificial intelligence, particularly within the financial sector and cryptocurrency markets, the ability for diverse AI agents to communicate and work together seamlessly is paramount. Our platform, Crypto Market AI, focuses on leveraging AI for market intelligence and trading. The principles behind AGNTCY—discovery, identity, secure messaging, and observability—are fundamental to building robust and trustworthy AI systems. As AI agents become more sophisticated, initiatives like the "Internet of Agents" will pave the way for more advanced applications, including AI-driven crypto trading bots and sophisticated market analysis tools that can interact and share insights across different platforms and services.

More to Read:

• AI Agents: Capabilities, Risks, and Growing Role
• AI-Driven Crypto Trading Tools Reshape Market Strategies in 2025
• The Future of Business Automation and Customer Engagement with AI Agents