AI Gateway Routing For All Agent Frameworks
If you're using an Agent that you built, a pre-built Agent (Claude Code, Ollama locally, etc.), or a provider-based Agentic UI (Gemini, ChatGPT, etc.), the question is - how do you
agentgateway
MCP Server oAuth: Implementation and Configuration
The running joke is "The S in MCP stands for security", and for good question. Out of the box, there's realistically no way to secure traffic from a user
Routing AI Traffic From Your IDE Through Agentgateway With Agentregistry
As teams and the enterprise are figuring out various ways to secure traffic from Agents to LLMs, other Agents, or MCP Servers, what about the lowest barrier to entry? Someone's local
Context-Aware Networking & Runtimes: Agentic End-To-End
AI network traffic can very much feel like a black box. You open an AI provider console or an Agent, ask a question or perform a task, and then what happens? Where does
Protecting Environments Implementing AI With Prompt Guards
You decide to start using AI and AI Agents within your environment. You use a chat/terminal feature, ask the Agent to do a few things, and get up to grab a cup