Glassy Capture 5:00
Installing and Configuring Companion
Install the Glassy Capture browser extension from the Chrome Web Store or Firefox, connect it to your account, pin it, and set up keyboard shortcuts for one-keystroke capture.
Glassy Learn
Master Glassy
in minutes
Bite-sized lessons on getting started, the Companion extension, local AI, and self-hosting — all offline-capable, all privacy-first.
The Getting-Started Tour
6:04 · 10 chapters · on-device, no tracking
What you'll see
A 6-minute walkthrough of every Getting-Started lesson — every screen, every action, in one take. Self-hosted, no third-party trackers, no cookies. Click a chapter below the player to jump straight to it.
Learn by track
Getting started
From sign-up to capture — everything you need to start.
Glassy Capture
Master the browser extension for friction-free capture.
Local AI
On-device intelligence, plus cloud and self-host paths.
Self-hosting
Run Glassy on your own server. Your data, your rules.
Second Brain
Your notes, readable by you and your agents.
Featured lessons
View all → Getting started 4:30
Welcome to Glassy
Create your Glassy account, sign in, and get oriented with the Today view and Account HUD — your home base for everything.
Local AI 6:00
How AI Works in Glassy
Understand how Glassy runs AI in your browser via WebGPU — two on-device runtimes, what they do, and when cloud AI is an option.
Second Brain 6:00
Connecting Your First MCP Client
Generate an MCP key, paste one config snippet, and ask Claude or Cursor a question about your own notes. Five minutes, no copy-paste afterward.
Self-hosting 8:00
Deploying Glassy with Docker
Deploy Glassy as a self-hosted single-user appliance with Docker Compose — six required environment variables and you're running in minutes.
Glassy Capture 6:30
Region Screenshots and the Element Picker
Capture specific page regions or individual DOM elements with pixel-perfect precision — HiDPI awareness, offscreen rendering pipeline, and CSS selector persistence.
Ready to get started?
See which plan fits your workflow, then jump into the first lesson.