LLMhop
Model Serving & MLOpsA tiny, stateless HTTP router that routes OpenAI‑compatible LLM requests to different backends based on the requested model.
Features
- OpenAI‑compatible reverse proxy and model router for self‑hosted or remote inference backends
- Serves native `GET /v1/models` and `GET /v1/models/{model}` discovery endpoints from configuration
- Stateless single‑binary Go service with zero external dependencies
- Supports authentication tokens, per‑model header injection, and request size limiting
Recent releases
View all 9 releases →Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Install & Platforms
Install via
go
docker
nix
Platforms
linux
