[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:siliconscope":3},"\u003Ch1>SiliconScope\u003C\u002Fh1>\n\u003Cp>\u003Cstrong>English\u003C\u002Fstrong> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002Fsiliconscope\u002Fblob\u002FHEAD\u002FREADME.de.md\" rel=\"nofollow ugc noopener\">Deutsch\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002Fsiliconscope\u002Fblob\u002FHEAD\u002FREADME.zh-CN.md\" rel=\"nofollow ugc noopener\">简体中文\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002Fsiliconscope\u002Fblob\u002FHEAD\u002FREADME.zh-TW.md\" rel=\"nofollow ugc noopener\">繁體中文\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002Fsiliconscope\u002Fblob\u002FHEAD\u002FREADME.ja.md\" rel=\"nofollow ugc noopener\">日本語\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002Fsiliconscope\u002Fblob\u002FHEAD\u002FREADME.ko.md\" rel=\"nofollow ugc noopener\">한국어\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fsiliconscope.calidalab.ai\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fwebsite-siliconscope.calidalab.ai-5c9efa\" alt=\"Website\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002FSiliconScope\u002Freleases\u002Flatest\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fkennss\u002FSiliconScope?color=2b9348\" alt=\"Release\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002FSiliconScope\u002Freleases\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fkennss\u002FSiliconScope\u002Ftotal?color=2b9348\" alt=\"Downloads\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002Fsiliconscope\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fkennss\u002FSiliconScope\" alt=\"License: MIT\" \u002F>\u003C\u002Fa>\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatform-macOS%2014%2B%20%C2%B7%20Apple%20Silicon-111\" alt=\"Platform\" \u002F>\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F57307\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Ftrendshift\u002Frepositories\u002F57307\u002Fdaily?language=Swift\" alt=\"#2 Swift Repository Of The Day\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>A \u003Cstrong>sudoless Apple Silicon system monitor\u003C\u002Fstrong> — a native SwiftUI dashboard \u003Cstrong>and\u003C\u002Fstrong> a full\nmenu-bar suite — with first-class \u003Cstrong>ANE (Neural Engine)\u003C\u002Fstrong>, \u003Cstrong>Media Engine\u003C\u002Fstrong>, and\n\u003Cstrong>memory-bandwidth\u003C\u002Fstrong> tracking that Activity Monitor and terminal monitors don't surface.\u003C\u002Fp>\n\u003Cp>Born from wanting to \u003Cem>see\u003C\u002Fem> how on-device AI and media workloads drive the Apple Silicon\naccelerators — and grown into a daily-driver monitor that can stand in for iStat Menus.\u003C\u002Fp>\n\u003Cp>\u003Cem>Featured on \u003Ca href=\"https:\u002F\u002Fapplech2.com\u002Farchives\u002F20260620-siliconscope-apple-silicon-mac-system-monitor.html\" rel=\"nofollow ugc noopener\">AAPL Ch.\u003C\u002Fa> (JP) and \u003Ca href=\"https:\u002F\u002Fwww.ifun.de\u002Fsiliconscope-ueberwacht-apple-ki-neural-engine-und-speicher-in-echtzeit-282222\u002F\" rel=\"nofollow ugc noopener\">ifun.de\u003C\u002Fa> (DE).\u003C\u002Fem>\u003C\u002Fp>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fkennss\u002Fsiliconscope\u002FHEAD\u002Fdocs\u002Fimg\u002Fdashboard.png\" alt=\"SiliconScope dashboard with the Replay scrubber\" \u002F>\u003C\u002Fp>\n\u003Cp>\u003Cem>The whole machine at a glance — an AI-workload bottleneck classifier, E\u002FP-core overlaid trends, GPU \u002F GPU-memory \u002F ANE \u002F Media, memory measured against the M1 Max's 400 GB\u002Fs ceiling, per-core temperatures, power, and live processes. The bar along the bottom is \u003Cstrong>Replay\u003C\u002Fstrong> (new in 3.0): every metric is recorded, so you can scrub back through a session like a DVR.\u003C\u002Fem>\u003C\u002Fp>\n\u003Ch3>Menu bar — every metric, iStat-style\u003C\u002Fh3>\n\u003Cp>Pin any card to its own menu-bar item — \u003Cstrong>CPU · GPU · Memory · Network · SSD · Sensors · Battery\u003C\u002Fstrong> — each with a live glyph and a rich dropdown. All sudoless.\u003C\u002Fp>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fkennss\u002Fsiliconscope\u002FHEAD\u002Fdocs\u002Fimg\u002Fmenubar.png\" alt=\"The per-metric menu-bar suite\" \u002F>\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fkennss\u002Fsiliconscope\u002FHEAD\u002Fdocs\u002Fimg\u002Fmenubar-gpu.png\" width=\"250\" alt=\"GPU \u002F Media \u002F Neural dropdown\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fkennss\u002Fsiliconscope\u002FHEAD\u002Fdocs\u002Fimg\u002Fmenubar-sensors.png\" width=\"250\" alt=\"Per-core temperatures\" \u002F>\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fkennss\u002Fsiliconscope\u002FHEAD\u002Fdocs\u002Fimg\u002Fmenubar-cockpit.png\" width=\"250\" alt=\"Combined SS cockpit — workload, all engines, trends, top processes\" \u002F>\n\u003C\u002Fp>\u003Cp>\u003Cem>The richest dropdowns. \u003Cstrong>GPU \u002F Media \u002F Neural\u003C\u002Fstrong> — GPU, GPU memory, ANE and Media as live meters plus a four-line 60-second trend. \u003Cstrong>Sensors\u003C\u002Fstrong> — per-unit temperatures from real \u003Cstrong>E-Core \u002F P-Core \u002F GPU \u002F Memory\u003C\u002Fstrong> sensors (curated SMC keys per chip generation, M1–M5; HID fallback elsewhere). \u003Cstrong>SS cockpit\u003C\u002Fstrong> — the whole machine in one dropdown: workload verdict, every engine, 60-second trends, and the top processes.\u003C\u002Fem>\u003C\u002Fp>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fkennss\u002Fsiliconscope\u002FHEAD\u002Fdocs\u002Fimg\u002Fbenchmark.png\" alt=\"Measuring a local model's speed and efficiency\" \u002F>\u003C\u002Fp>\n\u003Cp>\u003Cem>On-demand benchmark: \"Measure tok\u002Fs\" runs one short generation and reports the model's decode speed and energy efficiency — \u003Cstrong>tokens\u002Fsec · tokens\u002FWh\u003C\u002Fstrong> — stored per model.\u003C\u002Fem>\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>📊 \u003Cstrong>Measured tok\u002Fs on your Mac?\u003C\u002Fstrong> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkennss\u002FSiliconScope\u002Fdiscussions\u002F5\" rel=\"nofollow ugc noopener\">Post it in Discussions\u003C\u002Fa> — a crowd-sourced per-chip table helps others pick the right hardware.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch2>New in 3.0\u003C\u002Fh2>\n\u003Ch3>🧠 Process Inspector — per-process metrics, sudoless\u003C\u002Fh3>\n\u003Cp>Click any process to open the Inspector. It shows what Activity Monitor can't:\n\u003Cstrong>CPU (P\u002FE split) · IPC · per-process power (W) · memory · disk\u003C\u002Fstrong> — each with a live\nsparkline — and the one signal nobody else surfaces per process: \u003Cstrong>Neural-Engine memory\u003C\u002Fstrong>.\nSee exactly which app is on the ANE, and how much it's holding.\u003C\u002Fp>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fkennss\u002Fsiliconscope\u002FHEAD\u002Fdocs\u002Fimg\u002Finspector.png\" alt=\"Process Inspector — per-process CPU, IPC, power, and Neural-Engine memory\" \u002F>\u003C\u002Fp>\n\u003Cp>*An on-device transcription app running live (rig\u003C\u002Fp>\n",1784564568918]