agentgateway v1.5.0: Per-Key LLM Budgets That Return 429
agentgateway v1.5.0 shipped on 2026-08-27 with two controls that attach to the API key rather than the route: a rolling spend budget that blocks with an HTTP …
Read more →#Generative AI
12 posts
MCP Agent Identity: One Spec Shipped, Three Still Open
The Model Context Protocol roadmap published on August 22 names agent identity and enterprise-ready security as a priority workstream, with four specific …
Read more →SPIFFE Workload Identity for AI Agents, End to End
I built a demo where an AI agent calls a model and nothing in the path holds a certificate file. Not the agent, not the gateway, not the model upstream. Every …
Read more →Your AI Agent Should Not Hold the LLM API Key
I built a demo where an agent calls an LLM and has no LLM credential anywhere in its process. No API key in the environment, no key file on disk, nothing in …
Read more →Multi-Tenant MCP Federation with agentgateway
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 →Capping LLM Spend at the AI Gateway: Budgets and 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 →Governing an LLM-Driven Robot Fleet with agentgateway
I built a simulated warehouse robot fleet where LLMs do the planning and every piece of traffic that crosses the network runs through one open source gateway. …
Read more →Revenant: A Gateway-Native, Always-On Agent Runtime
Always-on personal agents keep dying the same three deaths: leaked keys, runaway spend, and silence. The first two get the headlines. The third one is the one …
Read more →Thousands of AI Agents on Tens of Pods: kagent Agent Substrate
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 →Building an LLM Agent Playground: A Deep Dive into AI Orchestration and Evaluation
Introduction In the rapidly evolving landscape of artificial intelligence and machine learning, Large Language Models (LLMs) have emerged as powerful tools for …
Read more →How to Get Ready for the AI Revolution: Embrace, Learn, and Innovate
The advent of generative AI is not something to be feared—it’s an exciting opportunity to elevate your business and career. Getting ready for this …
Read more →