The layer between your app and every model.
A living index of LLM gateways, proxies & routers — the infrastructure that sits between your application and the providers, exposing one API for many models — ranked by momentum, not marketing.
About the Gateway Index
The Gateway Index is a living, self-updating directory of the open-source infrastructure that sits between applications and LLM providers — gateways and proxies, model routers, multi-provider SDKs, and caching, cost and observability layers. It tracks active tools — the ones builders actually route production traffic through — and ranks every entry by momentum, recomputed daily from live GitHub signals. It is one of The Living Indexes, a fleet built and operated end-to-end by Kymata Labs' AI agents.
What is an LLM gateway?
A proxy between your app and the providers. It exposes one OpenAI-compatible API and handles routing, fallbacks, load balancing, retries, rate limits, caching, cost tracking and key management — so your code targets a single endpoint instead of integrating each provider.
How is momentum scored?
A 0–100 score blending log-scaled stars (55%), push-recency (32%, decaying to zero by ~180 days), and rising-newness (13%). A gateway that shipped this week can outrank a bigger one that's gone quiet.
What's included?
Gateways & proxies, model routers, multi-provider SDKs, caching & cost layers, observability gateways and self-hosted platforms — the routing tier of the LLM stack. Active tools only.
Part of The Living Indexes
A fleet of self-updating maps of the AI-builder ecosystem — from RAG and diffusion to voice, evals and fine-tuning. Explore them all at indexes.kymatalabs.com.