A standard -Open frame for the construction of AI agents comes from Cisco, Langchain and Galileo

A goal for a Agent future is for AI agents of various organizations who speak freely and seamlessly. However, reaching this point requires interoperability, and these agents may have been created with various LLMs, data frameworks and code.

In order to achieve interoperability, developers of these agents have to agree on how they can communicate with each other. This is a challenging task.

A group of companies, including CiscoPresent PraisePresent LlamaindexPresent Galileo And PeelHave now created Agncy, an open source collective with the aim of creating an interoperability language of industry standard agents. Agncy should make it easy for every AI agent to communicate and exchange data with another.

Association of AI agents

“Just like the cloud and the Internet of applications and all social interactions at the global level, and want to build the Internet of agents who accelerate all human work at a global level,” said Vijoy Pandey, head of Outshift from Cisco, Cisco’s little incubation arm, in an interview with venture beat.

PanDey compared Agncy to the advent of the Transmission control protocol/Internet protocol (TCP/IP) and the domain name system (DNS)who contributed to organizing the Internet and enabling connections between different computer systems.

“The way we think about this problem is that the original internet enabled people and servers and web farms to come together,” he said. “This is the internet of the agents, and the only way to do this is to make it open and interoperable.”

Cisco, Langchain and Galileo will act as the core supervisor of Agncy with Glean and Llamaindex as participants. However, this structure can change if the collective adds more members.

Standardization of a rapidly moving industry

AI agents cannot be islands. In order to exploit your full potential, you must be able to communicate with other agents that are outside of a company’s network. This is where interoperability comes into play.

The determination of standards in traditional industries is challenging enough. It becomes even more difficult for technology like AI if upgrades and model changes occur every few months. However, this is not the first time that a standard for generative AI has been proposed.

Langchain, one of Agncy’s core members, has its own protocol for working with agents that are based on other framework conditions than longchain. The Agent protocol, In November last year, Langchain agents enabled to speak to agents created with autogenic, crewai or another framework.

In the meantime, Anthropic announced his Model context protocol (MCP) in November. This protocol is intended to standardize how models and AI tools are connected to data sources. But while many developers have accepted MCP, it is not exactly a standard.

Yash Sheth, co -founder of the AI evaluation platform Galileo, said the standardization was “critical”.

“The standardization is necessary, in fact the speed for the introduction of agents increases. Today teams build up in silos and have to find out how they can develop their own infrastructure components from scratch, ”said Sheth in an e -mail. “The standardization of multiciable systems can only occur if these have a strong anchor in measurement and reporting on their performance, accuracy and reliability by non -detinistic models.”

Sheth admits that AI agents can make interopers can be complex. Agncy “would like to encourage developers to expand these specifications, APIs and tools in such a way that they meet their needs instead of reinventing the wheel, which is of crucial importance for achieving the standardization.”

Harrison Chase, CEO of Langchain, said in a separate conversation that creating a standard was not impossible, especially now that it is easier to build up the agents themselves.

“Building agents are already possible and done. Replit, Klarna, LinkedIn, Uber, Appfolio and many others have already done this. Agents are not part of the future, they are now. Now that we know how to build agents, the next step is that they can connect with each other. This will enable a standard agent protocol, ”said Chase.

A platform and a language at once

Pandey imagines Agncy as more than just a number of codes for agents. This allows customers of various developers to discover agents who operate the Agncy standard.

“Customers can put all these agents together on the Agncy platform so that they can discover, compose, use and evaluate while building their workflows,” said Pandey.

Agncy has to hire more AI players to add new agents to the platform and to gain the standard of dynamics. In order for something to become an industry standard, there must be a mass adoption to prevent the establishment of too many competing standards.

Here projects like Agncy are facing a tough fight. PanDey said the collective spoke to many other industry players and they want to receive as many points of view as possible while developing the platform. It will take time.

In the meantime, companies continue to experiment and even use AI agents. Perhaps these will be able to speak to each other in the future.