LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar.
Cost / License
- Free
- Open Source (Apache-2.0)
Application type
Platforms
- Mac
South Korea


LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar.


Janus is a single Go binary that runs .gguf models on your machine and exposes an OpenAI-compatible API. Point Cursor, Cline, or any local or cloud LLM, or AI tool with compatible OpenAI API endpoints at localhost — no Python, no Docker.