Kong

Active
GitHub Lua Apache-2.0

Description

The cloud-native API and AI Gateway providing LLM request routing, rate limiting, load balancing and observability for AI agent applications.

Key Features

  • API Traffic Management — Advanced routing, load balancing, health checks via RESTful Admin API or declarative config
  • AI Gateway Capabilities — Universal LLM API routing across OpenAI, Anthropic, Gemini, Bedrock and more
  • MCP Traffic Governance — MCP security, observability, and auto-generation from any RESTful API
  • Authentication and Authorization — JWT, OAuth, basic auth, ACLs and more authentication methods
  • 60+ Plugins — Rate limiting, request transformation, logging, monitoring and rich plugin ecosystem
  • Native K8s Support — Runs natively on Kubernetes via the official Ingress Controller

Use Cases

💡 Provide unified API gateway and traffic entry point for microservice architectures
💡 Implement unified multi-LLM provider access and load balancing in AI applications
💡 Protect MCP and AI service traffic with security and access control
💡 Apply rate limiting, circuit breaking and observability monitoring to API and AI services
💡 Deploy and manage API gateways in Kubernetes environments

Tags

observability api agent lua devops

Categories

📊 Observability

Quick Start

# Start Kong with Docker
git clone https://github.com/Kong/docker-kong
cd docker-kong/compose/

# Start the Gateway
docker-compose up -d

# Access Kong Admin API
curl http://localhost:8001/services

# Open Kong Manager UI
open http://localhost:8002
Visit GitHub Visit Website

Related Projects