×
Cisco, LangChain, and Galileo launch AGNTCY to bring order to agentic AI chaos
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

A new consortium aims to bring order to the rapidly multiplying world of AI agents by creating standardized frameworks that enable them to work together across platforms. This initiative, launched by Cisco‘s R&D division (Outshift), agent orchestration specialist LangChain, and trust and observability expert Galileo, addresses a critical need in AI development: while individual AI agents can handle simple tasks, their true potential lies in collaboration—but without standards, this potential remains largely untapped.

The big picture: Cisco, LangChain, and Galileo have founded AGNTCY, an open-source collective building infrastructure for what they call “a Cambrian explosion of AI agents,” referencing the period 500 million years ago when complex life rapidly diversified on Earth.

  • The consortium aims to define and build an open, interoperable “Internet of Agents” that can work across different vendors and organizational boundaries.
  • This standardization effort could transform the AI agent ecosystem from a potential free-for-all into a more structured, plugin-based environment.

Key details: AGNTCY is focusing its initial work on three foundational components designed to enable agent discovery, description, and communication.

  • An “agent directory” will function like an app store, allowing users to search for agents based on specific capabilities while providing reputation and quality metrics.
  • The “open agent schema framework” will establish a metadata format describing agent capabilities, enabling directories and discovery tools to catalog available options.
  • The “Agent Connect protocol and SDK” will serve as an interoperability layer allowing agents from different vendors to exchange messages, share context, and manage state.

Why this matters: Standardizing how AI agents interact addresses a critical gap in the rapidly evolving AI landscape, potentially preventing fragmentation while enabling more complex collaborative workflows.

  • Without established protocols for agent interaction, organizations face increasing complexity managing multiple disconnected AI systems.
  • Standardization could accelerate adoption by making it easier to discover, deploy and orchestrate AI agents across organizational boundaries.

Resources available: AGNTCY has established multiple channels for the developer community to engage with and contribute to these emerging standards.

  • Detailed specifications for both the Agent Directory and Open Agent Schema Framework are available on GitHub.
  • The consortium’s website (agntcy.org) provides additional information on the initiative and ways to participate.
How Cisco, LangChain, and Galileo aim to contain 'a Cambrian explosion of AI agents'

Recent News

College-educated Americans earn up to $1,000 weekly fixing AI responses

College graduates find lucrative opportunities in Silicon Valley's latest niche: fixing chatbots' grammar and tone to sound more natural.

Insta-pop: New open source AI DiffRhythm creates complete songs in just 10 seconds

Chinese researchers unveil an AI model that generates fully synchronized songs with vocals from just lyrics and style prompts in seconds.

New open-source math AI model delivers high performance for just $1,000

An open-source AI model matches commercial rivals at solving complex math problems while slashing typical training costs to just $1,000.