Unlike Microsoft Recall (closed, needs $1000+ hardware) or Screenpipe (requires separate OCR + Whisper + external LLM), ScreenMind uses one local Gemma 4 model for everything — screen vision, audio transcription, chat, and reasoning. No cloud, no telemetry, no accounts. Captures only when content changes. Search or chat with your full screen history in plain English. Build automations in Markdown. Runs on a 4GB GPU. MIT licensed, pip install.

ScreenMind captures your screen when content changes, analyzes every screenshot with Gemma 4 vision AI running locally, and lets you search or chat with everything you've ever seen on your computer. Ask "what was that error I saw 2 hours ago?" and get the actual answer from your screen history. It also auto-transcribes meetings, records voice memos, tracks where your time goes, and lets you build automations in plain English. No cloud. No accounts. No data leaves your machine. Runs on a 4GB GPU