- OmniRoute by cheaper-inference, 88k stars. Single endpoint gateway routing requests to hundreds of LLM providers
- litellm by BerriAI, 63k stars. Gateway and Python SDK that calls 100+ LLM APIs in OpenAI format
- freellmapi by tashfeenahmed, 52k stars. OpenAI-compatible gateway that routes requests across free LLM providers with failover
- new-api by QuantumNous, 52k stars. Self-hosted LLM gateway with OpenAI and Claude compatible APIs and usage logs
- 9router by decolua, 32k stars. Local gateway that routes coding tool requests across many AI providers
- agentgateway by agentgateway, 6.2k stars. Proxy for AI agent and MCP server traffic, written in Rust
- router by weave-os, 5.6k stars. Model router that sends each prompt to a chosen model via endpoint
- CPA-Manager-Plus by seakee, 4.1k stars. Self-hosted dashboard for AI gateway usage, cost, quota and account health
- WindsurfAPI by dwgx, 3.1k stars. Proxy that exposes Windsurf models through OpenAI and Anthropic style APIs
- Agent2API by aimod-cc, 2.3k stars. Local gateway that exposes AI coding clients as OpenAI and Anthropic APIs
- future-agi by future-agi, 2.3k stars. Self-hostable platform for tracing, evaluating and guarding LLM and agent apps
- GoModel by ENTERPILOT, 1.3k stars. Go gateway exposing one OpenAI-compatible API over many model providers
- otari by mozilla-ai, 930 stars. Self-run AI gateway with one endpoint for 40+ providers, keys and budgets
- respan-gateway by respanai, 841 stars. Rust gateway that routes one API endpoint to OpenAI, Anthropic, Gemini and others
- dario by askalf, 591 stars. Local proxy that sends coding agent and SDK calls via Claude or ChatGPT plans
- opengrok by OnlyTerp, 514 stars. Setup tool and model picker for running many LLM providers in one bot
- uncensored-ai-api by routerhubSI, 406 stars. Gateway API for Claude, GPT, Gemini and others, with abliterated model variants
- TurboLLM by mohitsoni48, 296 stars. Runs local LLMs tuned to your GPU, with a web UI and OpenAI-compatible API
- aistupidmeter-web by StudioPlatforms, 113 stars. Web app showing continuous LLM benchmarks, drift detection and routing
- bash4llm by kamaludu, 67 stars. Bash command line client for LLM APIs with no runtime dependencies
New repos every two days, stars refreshed daily. Visits are counted without cookies, and the numbers are public. How it works Data RSS Newsletter