Splash Monitor
A native macOS menu bar and desktop app that monitors Inco AI's Splash local inference engine, showing live token throughput, memory use, and installed models, and offering one-click model installation and server control.
Splash Monitor is a native macOS app for Inco AI's Splash local inference engine, which previously could only be operated from the command line. It adds a menu bar icon and a native window with real-time dashboards, model management, and server controls.
The dashboard shows prefill and decode speed, KV cache hit rate, speculative decoding acceptance, and latency percentiles, plus a live view of unified memory usage and GPU core detection. A model manager lists installed models with disk usage and browses the Hugging Face catalog for one-click installs. Users can switch models, start or stop the server, and launch coding agents such as Claude Code, OpenCode, and Codex against it, with an OpenAI-compatible endpoint.
It requires Splash to already be installed via Homebrew, supports macOS 13.0 and later on Apple Silicon, and automatically follows the system language between Spanish and English.