yosephyne/stratoscope
A live gauge for your local LLM inference engine in the menu bar: prefill and decode speed, prompt-cache hits, context, RAM and GPU. Works with Strata.
GitHub repository with 8 stars and 1 forks.
Language: C#
Topics: appkit, inference-monitor, kv-cache, llm, llm-inference, local-ai, local-llm, macos, menu-bar, menubar-app