Overview
What ScreenMind does
ScreenMind captures your screen, understands it with a single local model, and turns it into a searchable, chat-able memory of everything you do — all on your machine.
1,500+
DOWNLOADS
~180
GITHUB STARS
4 GB
MIN VRAM
MIT
LICENSE
📸
Smart capture
Content-change detection with perceptual hashing — it captures when the screen actually changes, not on a dumb timer.
🔬
Gemma 4 vision
Every frame analyzed into structured info: app, activity, mood, a rich scene description, and layout regions.
🔍
Hybrid search
Semantic embeddings (MiniLM) fused with FTS5 keyword search. Find things by meaning, not just exact words.
💬
Chat with memory
Conversational RAG over your history with follow-ups, and a vision fallback that reads the screenshot when text isn't enough.
🧠
In-app Model Hub
Download, switch and manage models from the UI with live progress — no terminal. Chat/Summary stay locked until the model is ready.
🎙️
Voice memos
Hold a hotkey and talk — Gemma 4's native audio encoder transcribes it, with a screenshot captured alongside.
🎤
Meeting transcription
Auto-detects Zoom/Teams/Meet/Discord, records mic + system audio, transcribes, and writes a structured summary.
📊
Analytics & Rewind
Category breakdowns, top apps, an hourly heatmap, and a timelapse player to scrub through your whole day.
🤖
Agents
Automations in plain-English Markdown or full Python. Drop a file in the agents folder and it runs on a schedule.
🔌
MCP + integrations
Expose your history to Claude/Cursor/VS Code over MCP; push summaries to Obsidian, Notion, or webhooks.
🔒
Private by design
100% local, zero telemetry, encryption at rest, and automatic redaction of cards / API keys / passwords.
⌨️
System hotkeys
Bookmark a moment, pause/resume capture, or record a voice memo — all with global shortcuts.
🔔
Smart notifications
Gentle nudges — distraction alerts, break reminders, and keyword auto-bookmarks like 'git push' or 'deploy'.
🧑💻
Dev-aware
Detects your git repo, branch and recent changes while you code, so coding activity is tracked with real context.
How it compares
Microsoft showed the world wants screen-aware AI with Recall — but it drew heavy privacy backlash. ScreenMind is the open-source, fully-local alternative to Recall and Screenpipe.
| ScreenMind | Screenpipe | MS Recall | |
|---|---|---|---|
| License | MIT — fully open | Source-available (paid for commercial) | Proprietary |
| Cost | Free forever | Free personal / paid commercial | Needs $1000+ Copilot+ PC |
| Privacy | Zero network, zero telemetry | Local-first, optional cloud | Telemetry opt-in |
| Min hardware | Any GPU ≥4 GB (or CPU) | 8 GB RAM, modern CPU | 40 TOPS NPU + 16 GB RAM |
| AI architecture | One model — vision+audio+reasoning | OCR + Whisper + external LLM | Proprietary NPU model |
| Audio / meetings | Native (Gemma audio encoder) | Whisper-based | Not supported |
| Search | Semantic + FTS5 hybrid | Semantic + keyword + a11y | Semantic only |
| Chat with memory | Full RAG + follow-ups | ✗ | ✗ |
| Agents | Markdown + Python + MCP | Pipes (TS) + MCP | ✗ |
| Encryption | AES (Fernet) + OS keyring | Optional | TPM + BitLocker |
| Platform | Windows / macOS / Linux | Windows / macOS / Linux | Windows 11 only |
Fun fact: the whole thing was built and benchmarked on a 4 GB GTX 1650 — the model literally spills into system RAM and still works. Any GPU with ≥6 GB runs it 3–5× faster.
↯ back to the brain