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.
#intermediate
Lessons tagged "intermediate"
18 results
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.
Local AI 5:30
Related Notes and Smart Tags
Discover how Glassy runs 384-dimensional embeddings in your browser via WebGPU to power Related Notes and Smart Tag Suggestions — no cloud, no data leaving your machine.
Self-hosting 5:00
How Your Local Account Works
Understand the separation between your self-hosted appliance and the Glassy cloud — account verification, local JWT auth, and the 30-day verification cache.
Glassy Capture 4:30
The Capture Queue
Understand how the Glassy Capture offline queue works — persistent storage in chrome.storage.local, automatic 60-second flush, badge counts, and manual queue management.
Local AI 6:00
Asking AI About Your Library
Use Glassy's AI assistant to ask questions about everything you've saved — with answers grounded in your actual notes, bookmarks, and captures, complete with source citations.
Second Brain 6:00
Walking the Knowledge Graph
Backlinks, neighborhoods, shortest paths, orphaned notes and the hubs your thinking orbits — the questions text search cannot answer.
Self-hosting 6:30
Configuration and Multi-Device Access
Configure environment variables, change ports, set up CORS, and access your self-hosted Glassy from your phone or other devices via Tailscale, Cloudflare Tunnel, or Caddy HTTPS.
Glassy Capture 4:00
Multi-Account Capture
Route captures to different Glassy accounts from the same browser extension using the account picker — personal and work accounts side by side.
Local AI 5:00
Cloud AI and Smart Routing
How Glassy Cloud routes AI queries to cloud providers when local models can't handle the job — and what that means for your privacy and costs.
Second Brain 6:00
Teaching an Agent to Remember
Durable memory that is a real note, recall scoped to the right agent, and session digests you can read — memory without a second database.
Self-hosting 5:30
Backups and Data Management
Protect your self-hosted Glassy data with automated daily backups, optional AES-256-GCM encryption, manual backup and restore, and storage monitoring.
Local AI 5:30
BYOK: Your Own API Keys
Bring your own API keys for OpenAI, Anthropic, and Gemini to bypass Glassy Cloud's AI cost caps and use the models you already pay for.
Self-hosting 5:00
Upgrades and Troubleshooting
Keep your self-hosted Glassy updated with docker compose pull or auto-update with Watchtower, check container health, and diagnose common issues.
Local AI 6:00
Ollama: Local Models on Your Server
Run capable LLMs like Llama and Qwen on your self-hosted Glassy server via Ollama — no API costs, no data leaving your machine, optional GPU acceleration.
Self-hosting 7:00
Cloud Sync and Media Transfer
Pair your appliance with your cloud account, sync supported rows, and download missing media.
Local AI 4:00
AI Without Limits on the Appliance
How AI billing works on the self-hosted Glassy appliance — no metering, no cost caps, no system cloud keys. BYOK and Ollama are your paths to AI.