Kagenti - A Kubernetes Control Plane for AI Agents

SUMMARY: Morgan Foster talks about the Kagenti project, which enables an AI Agent agnostic framework for security, authentication, identity and zero-trust.

SHOW: 1011

SHOW TRANSCRIPT: The Reasoning Show #1011 Transcript

SHOW VIDEO: https://youtu.be/djFZruLEDiw

SHOW NOTES:

• Kagenti (homepage)
• Kagenti (use-cases)
• “Old Things that look like Agents”
• “What makes Agents different?”
• CNV - What Makes Agents Different?
• “Handing your phone to a stranger, why Agents need their own identity”

Topic 1 - Welcome to the show. Tell us a little bit about your background and areas you focus on today. 

Topic 2 - Tell us a bit about the Kagenti project and the types of challenges it’s trying to solve for Agentic AI deployments. 

Topic 3 - How much commonality exists between different Agentic frameworks that a common, agnostic agentic orchestration approach can work? And how much difference still exists and would drive companies to silo’d deployments? 

Topic 4 - How far should an Agentic Orchestration framework go, and what types of things do you expect will still be Agentic framework dependent? 

• Is Kagenti more of a control-plane element, or more of a data-plane element? 

Topic 5 - As Kagenti evolves, what are some of the adjacent things that people should be keeping an eye on that might be a dependency, or could shift the direction of the project?

FEEDBACK?

• Email: show @ reasoning dot show
• Bluesky: @reasoningshow.bsky.social
• Twitter/X: @ReasoningShow
• Instagram: @reasoningshow
• TikTok: @reasoningshow