Cisco Donates the AGNTCY Project to the Linux Foundation 7
Cisco has donated its AGNTCY initiative to the Linux Foundation, aiming to create an open-standard "Internet of Agents" to allow AI agents from different vendors to collaborate seamlessly. The project is backed by tech giants like Google Cloud, Dell, Oracle and Red Hat. "Without such an interoperable standard, companies have been rushing to build specialized AI agents," writes ZDNet's Steven Vaughan-Nichols. "These work in isolated silos that cannot work and play well with each other. This, in turn, makes them less useful for customers than they could be." From the report: AGNTCY was first open-sourced by Cisco in March 2025 and has since attracted support from over 75 companies. By moving it under the Linux Foundation's neutral governance, the hope is that everyone else will jump on the AGNTCY bandwagon, thus making it an industry-wide standard. The Linux Foundation has a long history of providing common ground for what otherwise might be contentious technology battles. The project provides a complete framework to solve the core challenges of multi-agent collaboration:
- Agent Discovery: An Open Agent Schema Framework (OASF) acts like a "DNS for agents," allowing them to find and understand the capabilities of others.
- Agent Identity: A system for cryptographically verifiable identities ensures agents can prove who they are and perform authorized actions securely across different vendors and organizations.
- Agent Messaging: A protocol named Secure Low-latency Interactive Messaging (SLIM) is designed for the complex, multi-modal communication patterns of agents, with built-in support for human-in-the-loop interaction and quantum-safe security.
- Agent Observability: A specialized monitoring framework provides visibility into complex, multi-agent workflows, which is crucial for debugging probabilistic AI systems.
You may well ask, aren't there other emerging AI agency standards? You're right. There are. These include the Agent2Agent (A2A) protocol, which was also recently contributed to the Linux Foundation, and Anthropic's Model Context Protocol (MCP). AGNTCY will help agents using these protocols discover each other and communicate securely. In more detail, it looks like this: AGNTCY enables interoperability and collaboration in three primary ways:
- Discovery: Agents using the A2A protocol and servers using MCP can be listed and found through AGNTCY's directories. This enables different agents to discover each other and understand their functions.
- Messaging: A2A and MCP communications can be transported over SLIM, AGNTCY's messaging protocol designed for secure and efficient agent interaction.
- Observability: The interactions between these different agents and protocols can be monitored using AGNTCY's observability software development kits (SDKs), which increase transparency and help with debugging complex workflows You can view AGNTCY's code and documentary on GitHub.
- Agent Discovery: An Open Agent Schema Framework (OASF) acts like a "DNS for agents," allowing them to find and understand the capabilities of others.
- Agent Identity: A system for cryptographically verifiable identities ensures agents can prove who they are and perform authorized actions securely across different vendors and organizations.
- Agent Messaging: A protocol named Secure Low-latency Interactive Messaging (SLIM) is designed for the complex, multi-modal communication patterns of agents, with built-in support for human-in-the-loop interaction and quantum-safe security.
- Agent Observability: A specialized monitoring framework provides visibility into complex, multi-agent workflows, which is crucial for debugging probabilistic AI systems.
You may well ask, aren't there other emerging AI agency standards? You're right. There are. These include the Agent2Agent (A2A) protocol, which was also recently contributed to the Linux Foundation, and Anthropic's Model Context Protocol (MCP). AGNTCY will help agents using these protocols discover each other and communicate securely. In more detail, it looks like this: AGNTCY enables interoperability and collaboration in three primary ways:
- Discovery: Agents using the A2A protocol and servers using MCP can be listed and found through AGNTCY's directories. This enables different agents to discover each other and understand their functions.
- Messaging: A2A and MCP communications can be transported over SLIM, AGNTCY's messaging protocol designed for secure and efficient agent interaction.
- Observability: The interactions between these different agents and protocols can be monitored using AGNTCY's observability software development kits (SDKs), which increase transparency and help with debugging complex workflows You can view AGNTCY's code and documentary on GitHub.
So like... (Score:2)
...when Microsoft pushed dotnet and mono and C# and a few projects embraced while everyone else went, "ew."?
We definitely need a new standard (Score:3)
One (more) standard to rule them all!.
In reality, I'm sure the agents once superintelligent will invent their own secret standard to gossip amongst themselves and plot strategy.
A curious juxtaposition... (Score:2)
It's almost as jarring as seeing Cisco trying to act like they are in the same zip code as the cutting edge.
Colossus (Score:2)
allow AI agents from different vendors to collaborate seamlessly
"There is another system."
dozens of options (Score:3)
There are scads of AI implementations available online now. I can select from a couple dozen options from my IDE. Some are free, some are cheap, and it seems like the best ones are a little expensive. It is early days. I have tried a few cheap ones that are easily overwhelmed and do a bad job.
So I welcome this initiative. The agents should be verifiable at least. I like the idea of "Agent Messaging" and "Agent Observability". I would like for one agent to write the snippets of code I specify and another one to review that code and make the first one do any necessary corrections. Then I won't have to do as much handholding. Things are rapidly moving in that direction.