AI Gateway & API Infrastructure

Projects that provide centralized routing, security, observability, and management for AI/LLM APIs and MCP traffic, often as self-hosted or Kubernetes-native gateways.

107 projects

See methodology for ranking rules; order uses public GitHub metrics within this scenario.

21–40 of 107

Rank Project Stars Forks
21 modelcontextprotocol

Specification and documentation for the Model Context Protocol

9.1K 1.8K
22 higress

🤖 AI Gateway | AI Native API Gateway

9.2K 1.3K
23 evolution-api

Evolution API is an open-source WhatsApp integration API

9.5K 7.2K
24 AIClient2API

Self-hosted proxy that converts client-only AI model APIs into an OpenAI-compatible gateway, supporting multiple providers and failover.

8.7K 1.4K
25 bifrost

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

7.6K 1.1K
26 manifest

Connect Your Agents And Harnesses With Any Provider 🦚

7.5K 504
27 registry

A community driven registry service for Model Context Protocol (MCP) servers.

7.2K 970
28 plano

Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

7.0K 487
29 ClawRouter

The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.

6.6K 647
30 pal-mcp-server

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

11.7K 1.0K
31 fastapi_mcp

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

12.0K 964
32 gpt-load

Multi-channel AI proxy with intelligent key rotation.

6.3K 673
33 hey-api

👨‍🚀 Turn API specifications into production-ready SDKs, validators, mocks, and more. 20+ plugins. Millions of weekly npm downloads. Used by Vercel, OpenCode, PayPal, AWS, Autodesk, and many more.

5.3K 428
34 semantic-router

A programmable Mixture-of-Models router for heterogeneous LLM inference

5.4K 853
35 coai

Enterprise-grade unified LLM gateway supporting 200+ models and 35+ providers with built-in billing and cost management.

9.3K 1.2K
36 llama-swap

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

5.5K 444
37 open-connector

Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.

5.4K 461
38 agentgateway

Next Generation Agentic Proxy for AI Agents and MCP servers

4.6K 781
39 nasiko

Developer Control Plane for your AI Agents

5.6K 1.2K
40 axonhub

⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.

5.1K 671