Open source. Open possibilities.

Apache APISIX is a dynamic, real-time, high-performance cloud-native API and AI gateway built on NGINX and etcd, offering dynamic routing, plugin hot-loading, multi-protocol support, and AI proxying for LLM workloads.

AI Gateway routes LLM requests intelligently by intent, cost, and provider health. Supports multi-tenant access, caching, failover, and observability — reducing costs and improving reliability for production AI apps.

OmniRoute is an open-source MIT-licensed AI gateway providing one unified endpoint to access 352+ AI providers and 1200+ models (150+ free tiers). It features quota-aware auto-fallback, token compression saving 15–95%, and integrates with Claude Code, Cursor, Cline, and other coding agents.

MultiRouter AI is an OpenAI-compatible gateway that routes chat requests across multiple AI providers with automatic failover and load balancing. Supports Groq, Cerebras, Gemini, OpenAI, and custom endpoints via YAML config.

Self-hosted multi-tenant AI platform combining a polished chat UI with an OpenAI-compatible LLM gateway: multi-provider channel routing with priority and weight-based load balancing, subscription and usage billing, admin dashboard, file parsing, and SearXNG web search.

一个专为 Cloudflare Workers AI 设计的零成本网关。通过多账号免费额度叠加、智能路由和熔断机制，将 Qwen3 等模型转化为标准 OpenAI API，支持 Cherry Studio 等客户端接入。

gateway is a headless AI gateway for OpenAI, enabling secure multi-user access, cost tracking, rate limiting, and PII redaction with minimal setup.

An AI API gateway and user portal customized for the SMBU campus network, developed based on New API. It supports campus email registration, a model market, tutorial access, and a feedback system.

LiteLLM is an open-source AI Gateway and Python SDK that provides a unified OpenAI-compatible interface for calling over 100 different LLM providers.

A local OpenAI-compatible API gateway supporting multi-provider routing, circuit breaking, Chinese error prompts, a visual management panel, and native desktop application delivery.

New API is a self-hostable LLM gateway that aggregates multiple AI providers and converts between OpenAI, Claude and Gemini API formats, adding multi-user auth, channel routing, retries and usage-based billing.

Local AI gateway routing requests across 16 providers with free-tier priority, automatic fallback, and full decision logging. Runs locally, no cloud telemetry.

Higress is a cloud-native AI-native API gateway built on Istio and Envoy, featuring Wasm plugin extensibility, unified LLM provider access, MCP server hosting, and Kubernetes ingress support.

Hyperstrate Server is a self-hosted enterprise AI gateway providing model routing, provider orchestration, and governance for production LLM traffic.

An LLM Gateway built with LiteLLM for unified access to multiple AI providers via OpenAI-compatible API, featuring routing, fallbacks, caching, cost tracking, and guardrails.

Kong Gateway is a cloud-native, platform-agnostic API, LLM and MCP gateway with plugin-based extensibility, routing, load balancing, authentication and AI traffic features.