iohann.s.titov@gmail.com Ivan S. Titov llama-swap is an OpenAI/Anthropic-compatible HTTP proxy that starts and stops local LLM inference servers (llama.cpp, vllm, mlx-server, etc.) on demand based on the requested model. Lets a single API endpoint serve many models without keeping them all resident in GPU/NPU memory. Install OpenRC init.d/conf.d files for a supervise-daemon-managed service Install a systemd template service unit (llama-swap@.service) Build and embed the Svelte web UI (pulls net-libs/nodejs; runs npm at build time, requires network access during compile). mostlygeek/llama-swap istitov/extra-stuff istitov/extra-stuff istitov/extra-stuff