Show HN: AI gateway open source integrated with cursor and open router

RouterFuel, an open-source AI gateway, is now in open beta, offering a single async proxy layer for 330+ models via direct integration and OpenRouter, with features like vector-based caching that cuts API spend by up to 40% and provider failover in microseconds. Built on Tokio and Axum, it reports p99 latency of 18ms, 2,155 requests per second, and 18.6k tokens per second, with a cache hit rate of 37%. The core is AGPL-3.0 licensed, with commercial licenses available, and all features are free during the preview.

🚀 RouterFuel is in open beta. All features are free during preview. RouterFuel is a single async proxy layer in front of every model provider you use — 330+ models via direct integration plus OpenRouter. Built on a Tokio and Axum network core, it multiplexes concurrent inference requests, negotiates provider failover in microseconds, and streams tokens back without adding measurable overhead. cargo install routerfuel · zero telemetry sent off-cluster · AGPL-3.0 core // quickstart 1. Install cargo install routerfuel 2. Run ROUTEFUEL API KEYS="sha256:test:testclient" \ DATABASE URL="postgres://..." \ ./routerfuel 3. Make your first request curl -X POST http://localhost:3000/v1/chat/completions \ -H "X-API-Key: test" \ -H "Content-Type: application/json" \ -d '{"model":"auto","messages": {"role":"user","content":"Hello "} }' p99 latency 18ms req / sec 2,155 tokens / sec 18.6k cache hit rate 37% active providers // architecture Every RouterFuel deployment ships with the same resiliency core — no add-on modules, no separate billing for the parts that keep your inference layer alive. Vector-matches incoming prompts against prior completions and serves near-duplicates from cache, cutting repetitive API spend by up to 40%. Trips automatically on provider error spikes or latency drift, rerouting in-flight and new requests to a healthy fallback provider with no dropped calls. Inject headers, rewrite request bodies, and track upstream server health parameters with a middleware chain that runs inline with zero added round-trips. Seamlessly route to any model OpenRouter supports. Automatic catalog sync means new models appear without code changes. // pricing Every tier ships the full resiliency core. All features are free during the open beta. For side projects and prototypes. Free Launching Soon For production workloads at scale. $15/mo Launching Soon For regulated and air-gapped environments. Custom Launching Soon // contact Questions, feedback, or want to talk deployment? Reach us directly. // licensing RouterFuel's core is licensed under AGPL-3.0. That works great for self-hosting and open-source use, but if you're embedding RouterFuel in a closed-source product or run into AGPL's network-use clause at your company, we offer a separate commercial/enterprise license with no copyleft obligations. Accounts launch after the open beta — join the waitlist to get notified the moment they're live. Not signed up yet? Free during the open beta. We'll email you when your access is ready. We'll email you as soon as your access is ready.