Linux Foundation adopts AGNTCY to standardise agentic AI
The Linux Foundation has announced that it is welcoming the AGNTCY project, an open source initiative aimed at standardising foundational infrastructure for open multi-agent artificial intelligence (AI) systems.
AGNTCY delivers core components required for discovery, secure messaging, and cross-platform collaboration among AI agents that originate from different companies and frameworks. The project has the backing of industry players including Cisco, Dell Technologies, Google Cloud, Oracle, and Red Hat, all of whom have joined as formative members under the Linux Foundation's open governance.
Originally released as open source by Cisco in March 2025 with collaboration from LangChain and Galileo, AGNTCY now includes support from over 75 companies. Its infrastructure forms the basis for the so-called 'Internet of Agents' - an environment where AI agents from diverse origins are able to communicate, collaborate, and be discovered regardless of vendor or execution environment.
The increasing adoption of AI agents across industries has led to concerns about fragmentation and the formation of closed silos, constraining agents' ability to communicate across platforms securely and efficiently. AGNTCY's infrastructure aims to address these issues by standardising secure identity, robust messaging, and comprehensive observability. This allows organisations and developers to manage AI agents with improved transparency, performance, and trust.
Compatibility is a focus for AGNTCY, which is interoperable with the Agent2Agent (A2A) project, also part of the Linux Foundation, as well as Anthropic's Model Context Protocol (MCP). The project supports agent discovery through AGNTCY directories, enables observable environments using AGNTCY's software development kits (SDKs), and utilises the Secure Low Latency Interactive Messaging (SLIM) protocol for secure message transport.
"The AGNTCY project lays groundwork for secure, interoperable collaboration among autonomous agents," said Jim Zemlin, executive director of the Linux Foundation. "We are pleased to welcome the AGNTCY project to the Linux Foundation to ensure its infrastructure remains open, neutral, and community-driven."
The AGNTCY project's infrastructure offers several key functions for multi-agent environments. Agent discovery is facilitated using the Open Agent Schema Framework (OASF), allowing agents to identify and understand each other's capabilities. Agent identity is supported via cryptographically verifiable processes to ensure secure activity across organisational boundaries. The agent messaging component supports various communication modes, including human-in-the-loop and quantum-safe options via the SLIM protocol. Observability functionalities provide evaluation and debugging across complex, multi-vendor workflows.
"Building the foundational infrastructure for the Internet of Agents requires community ownership, not vendor control," said Vijoy Pandey, general manager and senior vice president of Outshift by Cisco. "The Linux Foundation ensures this critical infrastructure remains neutral and accessible to everyone building multi-agent systems."
The project is underpinned by real-world applications, including AI-driven continuous integration and deployment pipelines, multi-agent IT operations, and the automation of telecom networks. This underlines the diversity of use cases benefitting from AGNTCY's open source approach.
Various leaders and members have shared their perspective on the announcement:
"Interoperability is central to Dell's agentic AI vision. The ability of agents to work together empowers enterprises to reap the full value of AI. Additionally, interworking technologies must accommodate agents wherever they are deployed whether in public clouds, private data centres, the edge or on devices. Dell is working hand-in-hand with industry leaders to establish open standards for agentic interoperability. Being a formative member of the Linux Foundation's AGNTCY project is one such step towards fulfilling the promise of agentic AI." – John Roese, global CTO and chief AI officer, Dell Technologies.
"We've been building AGNTCY's evaluation and observability components from day one because reliable Agents cannot scale without purpose-built monitoring. Moving all components of AGNTCY to the Linux Foundation ensures these tools serve the entire ecosystem, not just our customers. As a founding member of AGNTCY, we're eager to see neutral governance accelerate adoption of standards we know enterprises need for production agent deployments." – Yash Sheth, co-founder, Galileo.
"Open, community-driven standards are essential for creating a diverse, interoperable agentic AI ecosystem. We're pleased that Cisco is moving AGNTCY to the Linux Foundation, where it will be neutrally governed alongside the Agent2Agent protocol to advance powerful, collaborative agent systems for the industry." – Rao Surapaneni, vice president, business applications platform, Google Cloud.
"Enterprise customers need agent infrastructure they can trust for mission-critical workloads. We welcome AGNTCY's move to the Linux Foundation and are proud to be a formative member of this project. A tight control over data security and governance helps discovery, identity, and observability components work reliably across the entire enterprise technology stack, not just specific vendor ecosystems." – Roger Barga, senior vice president, AI & ML, Oracle Cloud Infrastructure.
"Our customers and partners, as well as the open source communities we work with, are actively exploring agentic capabilities to bring the inferencing benefits of vLLM and llm-d to their applications. Red Hat welcomes AGNTCY's move to the Linux Foundation and we look forward to working with the community to help bring open, agnostic governance to the agentic AI ecosystem." – Steve Watt, vice president and distinguished engineer, Office of the CTO, Red Hat.
