Run This Ai
EN DE

Envoy AI Gateway

Unified access gateway for generative AI services, built on Envoy Gateway (CNCF). Route, observe, and govern LLM traffic with enterprise-grade policy controls.

★ 1,976 GitHub Apache-2.0 ai-gatewayapi-gatewaycncfkubernetesllm LLM & Chat

Overview

Envoy AI Gateway is an open-source, CNCF-hosted gateway that gives you unified access to generative AI services. Built on Envoy Gateway, it lets you route requests to any LLM provider — OpenAI, Anthropic, AWS Bedrock, or self-hosted models — through a single consistent interface. It provides enterprise features like token-based rate limiting, cost control, observability, and centralized policy management, while keeping your vendor lock-in to zero. Deploy it on Kubernetes or run it standalone in Docker to manage, secure, and monitor all your AI traffic from one place.

Requirements

Min vCPU
2
Min RAM
2048 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
4096 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  envoy-ai-gateway:
    image: envoyproxy/ai-gateway-cli:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/envoy-ai-gateway:/data

Best VPS for Envoy AI Gateway →

Related tools

NextChat

Cross-platform ChatGPT web UI with multi-model support for Ollama, Claude, Gemini, and more

Lobe Chat

Extensible, open-source ChatGPT alternative with plugins, knowledge base, and multi-LLM support

Open WebUI

User-friendly WebUI for LLMs (Ollama, OpenAI API)

text-generation-webui

Run local LLMs with a powerful web interface — text, vision, tool-calling, and OpenAI-compatible API

Streamlit

Build and share data apps in pure Python — fast

Gradio

Build and share delightful machine learning apps in Python

Guides & articles

Envoy AI Gateway Tutorial: Route Your First LLM Request in Docker

Step-by-step tutorial to run Envoy AI Gateway with Docker, route requests to any LLM provider through a single gateway, and add token-based rate limiting — with a hands-on review.

Aug 30, 2026

Envoy AI Gateway: Unified Access to Generative AI Services

An open-source, CNCF-hosted gateway built on Envoy Gateway that routes, observes, and governs traffic to any LLM provider — OpenAI, Anthropic, Bedrock, or self-hosted models — through one consistent interface.

Aug 30, 2026