Fastllm-proxy
The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O on the request path, cache-affinity routing, RBAC, budgets and a 13-screen UI in the binary.
azrtydxb/Fastllm-proxy
View on GitHub ↗The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O on the request path, cache-affinity routing, RBAC, budgets and a 13-screen UI in the binary.
Fastllm-proxy grew +0.9% in the last 30 days, ranks 221st of 268 in LLM Gateway & Routing, actively maintained, last commit 2 days ago.
Star trajectory
64 days tracked+0.9% in 30d, below the LLM Gateway & Routing median of +2.1%.
Last commit 2 days ago, fresher than the median of 5d.
How it compares in LLM Gateway & Routing
Ranked 221st of 268 by stars.
- Language
- Rust
- License
- Apache License 2.0
- Contributors
- 2
- Forks
- 92
- Watchers
- 0
- Open issues
- 1
- Releases
- 2
- Created
- 2026-08-06
- Stars this week
- +1
You've seen where Fastllm-proxy stands today.
Get the moves before everyone else: the 5 LLM Gateway & Routing repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.