HomeProjectsArticlesPK BoardAbout
Explore Projects

Kgateway

Active
GitHub Go Apache-2.0

Description

Kgateway is an Envoy-based cloud-native API and AI gateway, proxying LLM APIs, internal services and multi-protocol traffic.

Key Features

  • Envoy data plane — high-performance Istio-compatible gateway
  • AI Gateway — LLM proxy and function calling
  • Multi-protocol — HTTP/1, HTTP/2, gRPC
  • Mesh-friendly — integrates with Istio and Linkerd
  • Observability — full metrics and tracing
  • CNCF sandbox — cloud-native standard project

Use Cases

💡 Unified entry for LLM and internal APIs
💡 Function-calling gateway on Kubernetes
💡 A unified gateway layer that fits existing service mesh
💡 Observable AI API traffic management

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (5.7k stars)
  • • Permissive open-source license (Apache-2.0)

Tags

gateway ai kubernetes envoy api

Categories

⚡ Agent Tools 🔄 Workflow

Quick Start

kubectl apply -f https://github.com/kgateway-dev/kgateway/releases/latest/download/standard-install.yaml
# 安装 CLI
kgatewayctl install
Visit GitHub Visit Website

Related Projects

AppFlowy

76.2k · Dart
Active A+

AppFlowy is an open-source Notion alternative with AI workflows, knowledge base, kanban and multi-device sync, usable as agent long-term memory.

note-takingproject-managementai +2
  • · Self-hostable — full data ownership, deploys locally or on a private server
  • · AI assistant — built-in AI for writing, summarizing, translating and table generation
  • · Knowledge base — nested pages, databases, linked views for structured notes
View full details → View on GitHub

LiteLLM

57.9k · Python
Active A

LiteLLM provides a unified interface and proxy gateway for LLM calls, simplifying multi-model switching, routing, and cost control.

llmgatewayproxy +1
  • · Unified LLM interface — OpenAI-format calls across 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, etc.)
  • · AI Gateway proxy server — Self-hosted proxy with virtual keys, spend tracking, load balancing, and admin dashboard
  • · Python SDK — Switch LLM providers in code via the completion() function
View full details → View on GitHub