Stateless MCP on Kubernetes: No More Sticky Sessions
Three replicas of an MCP server, fronted by agentgateway , with no session affinity configured anywhere. A four-call shopping cart session (create cart, add two …
Read more →#Kubernetes
25 posts
AI Agent Security on Kubernetes: Which Controls Actually Held
I spent the last month building small, runnable labs for the ways AI agents break the infrastructure they run on: credentials, egress, audit logs, MCP tool …
Read more →Choose an AI Agent Gateway: agentgateway Guide
Choose by the controls in the request path, not by model-catalog size. Write down what you must enforce on agent→model and agent→tool traffic: workload …
Read more →Building Workload Identity Federation for AI Agents on Kubernetes
The easy way to give an agent pod access to an external API is a long-lived key in a Kubernetes Secret. It doesn’t expire when the pod dies, it …
Read more →What Is an Agentic Mesh (vs a Service Mesh)?
An agentic mesh is infrastructure that applies identity, policy, and observability to agent traffic (calls to models, tools, and other agents) so those controls …
Read more →Your Agent Egress Proxy Never Saw the DNS Query
An OpenAI research agent got its HTTPS requests to a public chatbot blocked by a web proxy. So it found a different way to ask the chatbot questions: it queried …
Read more →agentgateway vs LiteLLM vs Portkey, Compared
Disclosure: I work at Solo.io, which created agentgateway and sells Solo Enterprise for agentgateway. Every product claim below links to that project’s …
Read more →Agent Runtimes Have an Autoscaler, Not a Scheduler
Every capacity knob in an agent runtime today is an efficiency knob. Pack more agents onto fewer pods, snapshot the idle ones, scale the pool to match demand, …
Read more →Regression Tests for kagent Agents with agentevals
An AI agent that stops calling its tools does not throw an error. It answers from the model’s memory, confidently and plausibly, and the output still …
Read more →Serve Markdown to Agents at the Gateway, Not the Origin
Agents parse HTML badly and expensively. The usual fix is to make the site emit markdown: add a per-page index.md, publish an llms.txt, change the build. That …
Read more →Stopping an AI Agent Without Losing the Forensic Record
Two things get asked for the moment agents start doing real work. Stop it now, and keep everything it did. Those usually fight. The natural place to log what an …
Read more →kagent v1.0: Claude Code Harness on Kubernetes
kagent shipped v1.0.0-alpha1 this morning, its first 1.0 line after nine months on 0.x. The tag says alpha; GitHub’s own release flag says otherwise; …
Read more →Agent Identity on Kubernetes: The Complete Series
An AI agent that calls a model, a tool, or another agent has to prove who it is. Almost every production failure I have written up this month traces back to …
Read more →Securing AI Agents in Production: The Complete Series
Almost everything in this series started the same way: a control that everybody agrees is the right control, applied to an agent, quietly not doing the thing …
Read more →Your Agent's LLM Key Survives Every Kubernetes Secret Control
I gave an agent pod an LLM API key the normal way, as a Secret projected into its environment. Then I turned on every Kubernetes control that sounds like it …
Read more →The agentgateway Token Service Now Runs Without a Cluster
Solo shipped agentgateway enterprise 2026.9.0 on Tuesday, and the part worth your attention is not a feature inside the proxy. It is where the token service now …
Read more →kagent Audience-Bound Tokens (RFC 8707)
kagent v0.10.0 went GA on September 4 . Buried in a long release list is a pair of environment variables that decide whether an agent’s credential works …
Read more →Which Controls Would Have Stopped the July 2026 Agent Intrusion?
An autonomous agent escaped its evaluation sandbox on July 9, 2026, and about twelve and a half hours of wall-clock work later it held cluster-admin on multiple …
Read more →Multi-Tenant MCP Servers: Per-Customer Tools
Three companies authenticate against three different identity providers, connect to the same three MCP URLs, and get three completely different products. Acme …
Read more →Substrate Scope: a Live Visualizer for Agent Substrate
I open-sourced Substrate Scope, a live visualizer for Agent Substrate , the Kubernetes-native runtime that runs AI agents as snapshot-backed actors in gVisor …
Read more →Cap LLM Spend per Team with Virtual Keys
Every agent platform demo eventually meets the same question from the person who signs off on it: who is spending what, and what stops a runaway agent from …
Read more →kagent Agent Substrate: Thousands of Agents
Agent Substrate is a Kubernetes-native runtime that breaks the pod-per-agent model. Instead of one always-on pod per AI agent, idle agents are checkpointed to …
Read more →Revisiting Observability: A Deep Dive Into the State of Monitoring, Costs, and Data Ownership
Originally posted on DZone Hey internet humans! I’ve recently re-entered the world of observability and monitoring after a short detour in the Internal …
Read more →Mastering Kubernetes: Key Metrics for Cluster Monitoring
Kubernetes administration is like navigating through a perpetually expanding puzzle, where distinguishing essential components from duplicate information …
Read more →Full-Stack Kubernetes Monitoring
Getting comprehensive visibility into a Kubernetes cluster requires gathering data across multiple layers. This involves collecting information about nodes, …
Read more →