Solo.io Blog

Are AI agents best deployed as Kubernetes Pods? Explore why agent-substrate introduces a new execution model built for scalable, ephemeral AI agents.

Compaction is what an agent does when it runs out of memory. Compression is what infrastructure does so agents don’t have to. They sound similar, they live in different layers, and conflating them is why most teams reach for the crudest option first.

In previous posts, I’ve covered the reasons why an AI agent needs an identity. I recommend reading that first. In this post I want to nail down “what is agent identity” because I’ve seen a lot of different interpretations from smart people such as “use OAuth” to “it’s just workload identity”, and new protocols cropping up, etc. But what “is” an agent identity in concrete terms?

Learn how to configure and test agentgateway Code Mode to expose APIs as MCP tools, enabling secure agent access without an MCP server.

What’s the difference between agent-sandbox and agent-substrate? Learn how these complementary projects help teams build AI agent platforms that are both secure and scalable on Kubernetes.

Learn why James Quigley's team adopted Istio Ambient for mTLS, security, and operational simplicity, and how the journey unfolded.

Learn how to run AI agents on Kubernetes with Agent Substrate and kagent. This step-by-step guide covers architecture, installation, configuration, and deploying agent workloads using the Substrate runtime.

Kubernetes transformed how we run services. Agent Substrate and kagent are transforming how we run AI agents with fast startup, efficient resource utilization, and secure execution.

Discover how to build a dollar-denominated AI cost-governance layer on top of agentgateway's native External Processing support. The reference implementation adds hierarchical budgets, pre-request reservations, actual-cost settlement, forecasting, approvals, rate limits, and a management UI.

Learn about the infrastructure challenges emerging around AI systems, why existing gateway patterns are being stretched in new ways, and why agentgateway was built as a unified, high-performance operational layer for AI and API traffic.