jundot/omlx: README-based editorial guide

jundot/omlx describes itself in the README as "LLM inference server with continuous batching & SSD caching for Apple Silicon , managed from the macOS menu bar". This article keeps to facts that can be checked in the repository. Stars, forks, and promotional badges are signals of attention, not proof of quality. Under "README", the README says: > Every LLM server I tried made me choose between convenience and control. I wanted to pin everyday models in memory, auto-swap heavier ones on demand, set context limits - and manage it all from a menu bar.. That establishes the project's stated boundary, not a production test.

The README's "Homebrew Service" section gives a useful starting point for deciding whether the project fits: Server log: /.omlx/logs/server.log (structured application log). If that problem is not yours, popularity is a poor reason to adopt it. Project names, commands, and component names are kept as written so a reader can return to the primary source without guessing at terminology. Another checkable README item is: Service log: $(brew --prefix)/var/log/omlx.log (stdout/stderr). It can shape a first test, but it does not replace testing in the intended environment.

The operating model is spread across sections such as "Homebrew". The source evidence includes: Optional GLM-5.2 / MiniMax M3 native custom kernels currently require a HEAD build:. This article does not turn missing architecture, performance, or security details into claims. A real deployment still needs a look at the repository layout, configuration files, and release history.

Start installation from the README's documented entry point. A command that can be checked in the source is: brew tap jundot/omlx https://github.com/jundot/omlx brew install omlx # Upgrade to the latest version brew update && brew upgrade omlx # Run as a background service (auto-restarts on crash) omlx start # Optional: MCP (Model Context Protocol) support /opt/homebrew/opt/omlx/libexec/bin/pip install mcp When the README contains no runnable command, this article does not invent one. Open its "macOS App" section and confirm system dependencies, default ports, and first-run initialization before using a public server.