IRLFirst physical meetup — Bengaluru, Sat May 23, 4PM · RSVP on Luma
HomeToolsMCPHow It WorksStoriesPhilosophyCommunityArchitectureStar on GitHub
All Tools
H
Dev ToolsFreemiumOpen Source

HIGRESS

AI Native API Gateway

Apache-2.0

ABOUT

Managing traffic to AI and LLM services requires more than a standard API gateway — it needs AI-native awareness of model endpoints, MCP protocols, token-based rate limiting, and provider routing. Higress, built on Envoy, gives teams a purpose-built gateway that handles model routing across providers, hosts MCP servers for agent tool integration, applies AI-specific rate limits, and provides observability — all in a single, Kubernetes-native deployment.

INSTALL
docker run -d --rm --name higress-ai -v ${PWD}:/data \ -p 8001:8001 -p 8080:8080 -p 8443:8443 \ higress-registry.cn-hangzhou.cr.aliyuncs.com/higress/all-in-one:latest

INTEGRATION GUIDE

1. Route and load-balance API calls across multiple LLM providers with automatic failover and fallback 2. Host and manage MCP servers for AI agents, converting OpenAPI specs into MCP endpoints 3. Secure AI API access with rate limiting, authentication, and token-based usage tracking 4. Monitor and observe AI traffic patterns, model usage, and gateway performance metrics 5. Deploy in Kubernetes with Helm for production-grade, auto-scaling AI infrastructure

TAGS

ai-gatewayapi-gatewayenvoycloud-nativekubernetesmcp
Higress — AI Tool | Agentic AI For Good