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

The rise of AI agents, which are autonomous programs capable of performing tasks without explicit step-by-step instructions, has brought a critical challenge to the forefront: interoperability. Ensuring that these disparate AI agents can effectively work together is paramount. Cisco’s AGNTCY (pronounced "agency") project is emerging as a significant solution to this challenge. To foster an open ecosystem and prevent fragmentation in AI agency development, Cisco has donated AGNTCY to the Linux Foundation, with support from industry leaders such as Dell, Google Cloud, Oracle, and Red Hat. The project aims to establish an open-standard infrastructure, envisioning an "Internet of Agents," which will enable diverse AI agents to communicate and collaborate seamlessly. Without universal standards, AI agents often remain isolated in silos, hindering their potential usefulness. History teaches that the development of such standards can either be dominated by a single entity or stalled by competing interests. The AGNTCY project seeks to avoid these pitfalls by creating a neutral, community-driven foundation, much like the TCP/IP protocol that was foundational to the internet. Vijoy Pandey, GM and SVP of Cisco’s Outshift, highlighted this focus on 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." AGNTCY was open-sourced by Cisco in March 2025 and has since garnered support from over 75 companies. Under the Linux Foundation’s neutral governance, the project is positioned to become an industry-wide standard. The Linux Foundation's track record in fostering consensus on complex technologies provides a strong foundation for AGNTCY's widespread adoption.

Core Components of AGNTCY

The AGNTCY framework addresses the complexities of multi-agent collaboration through several key components:

• Agent Discovery: The Open Agent Schema Framework (OASF) functions as a "DNS for agents," facilitating their discovery and understanding of each other's capabilities.
• Agent Identity: A cryptographically verifiable identity system ensures that agents can authenticate themselves and securely execute authorized actions across different vendors and organizations.
• Agent Messaging: The Secure Low-latency Interactive Messaging (SLIM) protocol is designed for complex, multi-modal communication patterns, including human-in-the-loop interactions and quantum-safe security.
• Agent Observability: A specialized monitoring framework provides crucial visibility into multi-agent workflows, which is essential for debugging probabilistic AI systems.
Jim Zemlin, Executive Director of the Linux Foundation, commented on the project's significance, stating, "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 Protocols

AGNTCY is designed to complement other emerging AI agency standards, such as the Agent2Agent (A2A) protocol and Anthropic’s Model Context Protocol (MCP). AGNTCY enhances interoperability by facilitating discovery, messaging, and observability across these protocols:
• Discovery: Agents using A2A and servers using MCP can be registered and discovered through AGNTCY's directories.
• Messaging: Communications that utilize A2A and MCP can be transported securely and efficiently via the SLIM protocol.
• Observability: AGNTCY's SDKs enable the monitoring of interactions, thereby increasing transparency and aiding in the debugging process.
Dell Technologies’ global CTO and chief AI officer John Roese underscored the importance of this interoperability, remarking, "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."

Community and Future Development

With the Linux Foundation now overseeing its development, AGNTCY is actively engaging its working groups and encouraging broader community participation to accelerate adoption. The project's code and documentation are openly available on GitHub, inviting contributions from developers worldwide.

---

Originally published at ZDNet on July 29, 2025.

Frequently Asked Questions (FAQ)

About AI Agents and Interoperability

Q: What are AI agents? A: AI agents are autonomous AI programs that can perform tasks and make decisions without requiring explicit step-by-step instructions from humans. Q: Why is interoperability important for AI agents? A: Interoperability is crucial to allow different AI agents, potentially developed by various entities, to communicate, collaborate, and work together effectively, preventing fragmented systems and maximizing their collective potential. Q: What is the goal of Cisco's AGNTCY project? A: The primary goal of AGNTCY is to create an open-standard infrastructure, an "Internet of Agents," that enables seamless communication and collaboration between diverse AI agents, preventing fragmentation and promoting widespread adoption. Q: How does AGNTCY aim to achieve interoperability? A: AGNTCY utilizes core components like Agent Discovery (OASF), Agent Identity, Agent Messaging (SLIM), and Agent Observability to create a standardized framework for AI agent interaction.

AGNTCY Project Details

Q: Who supports the AGNTCY project? A: The AGNTCY project is supported by industry leaders including Dell, Google Cloud, Oracle, and Red Hat, and has attracted support from over 75 companies since its open-sourcing. Q: What is the Open Agent Schema Framework (OASF)? A: OASF is a component of AGNTCY that acts like a "DNS for agents," enabling them to discover and understand each other's capabilities. Q: What is the role of Agent Identity in AGNTCY? A: Agent Identity provides a cryptographically verifiable system that allows agents to prove their authenticity and securely perform actions across different systems and organizations. Q: What is the SLIM protocol used for in AGNTCY? A: SLIM (Secure Low-latency Interactive Messaging) is the protocol used for agent messaging, supporting complex, multi-modal communications, including human-in-the-loop interactions and quantum-safe security. Q: How does AGNTCY relate to other AI agent protocols like A2A and MCP? A: AGNTCY complements these protocols by facilitating discovery, messaging, and observability across them, allowing agents using A2A and MCP to be discovered and communicate more efficiently.

Crypto Market AI's Take

The development of a standardized infrastructure like AGNTCY is a critical step towards unlocking the full potential of AI agents. In the cryptocurrency space, where rapid innovation and complex data analysis are common, interoperable AI agents could revolutionize how markets are analyzed, trades are executed, and risks are managed. Imagine AI agents collaborating to predict market shifts, execute complex trading strategies across multiple exchanges, or even automatically rebalancing portfolios based on real-time sentiment and news analysis. Our platform at Crypto Market AI is deeply invested in leveraging AI for these very purposes, aiming to provide users with sophisticated tools that enhance decision-making and operational efficiency. The principles behind AGNTCY, such as open standards and community collaboration, align with our vision of fostering a more interconnected and intelligent financial ecosystem. For those interested in the practical application of AI in finance, our insights into AI-driven crypto trading tools and the broader impact of AI agents in the workplace offer further context.

More to Read:

• Understanding the Role of AI Agents in Modern Business Automation
• The Future of Finance: How AI is Revolutionizing Cryptocurrency Markets
• Navigating Crypto Regulations: A Global Overview
• The Evolving Landscape of AI in Cybersecurity