Technology · Ebook

Higress: The AI-Native API Gateway

by Shriira Press

Higress is a cloud-native API gateway built on the Envoy proxy and the Istio control plane, born inside Alibaba's production infrastructure and now a CNCF sandbox project. It folds three gateways that organizations usually run separately — the traffic gateway at the cluster edge, the microservices gateway in front of internal services, and an emerging AI gateway in front of large language models — into one system with a single configuration model and console. This book traces that story from the Nginx-reload problem that motivated it, through the Envoy-and-Istio architecture and control plane, routing via Ingress and the Gateway API, service discovery and the McpBridge, the WebAssembly plugin system, and the AI gateway: unified LLM routing, token rate limiting, semantic caching, and MCP server hosting, closing with operations and migration.

Contents

1. 1Preface
2. 2Chapter 1 — What Higress Is
3. 3Chapter 2 — Architecture: Envoy and Istio
4. 4Chapter 3 — The Control Plane and Configuration Flow
5. 5Chapter 4 — Routing: Ingress and the Gateway API
6. 6Chapter 5 — Service Discovery and the McpBridge
7. 7Chapter 6 — The WebAssembly Plugin System
8. 8Chapter 7 — The AI Gateway
9. 9Chapter 8 — MCP Servers and Agent Tooling
10. 10Chapter 9 — Operations, Migration, and the Ecosystem