ssorg.dev: I Built a Local AI Librarian for All Those Screenshots I Keep Forgetting About 🦥

Description and use

ssorg.dev is a local AI-powered screenshot organizer that extracts text, generates metadata, and stores data in SQLite, enabling quick retrieval without cloud data transfer.

Problem

Users accumulate many screenshots with useful information but lack a way to locate specific images quickly.

Outcome

ssorg.dev transforms a chaotic screenshot collection into a searchable knowledge base, enabling quick retrieval via keyword search or QA, while keeping all data local for privacy.

Workflow

• Upload screenshots
• Extract text using Tesseract OCR
• Generate summaries and metadata with local Gemma 3 4B via Ollama
• Store results and images in SQLite and local library
• Search by keywords or ask questions about relevant screenshots

Evidence

We all have that one folder: hundreds of screenshots, useful information buried somewhere, and absolutely no idea where to find a particular image when we need it.

Source

ssorg.dev — a local-first, AI-powered screenshot organizer that helps turn a messy screenshot collection into a searchable personal knowledge library.

Source

Extract text with OCR: Reads text from screenshots using Tesseract.

Source

Organize with local AI: Uses Gemma 3 4B through Ollama to help generate summaries and structured metadata.

Source

Build a searchable library: Stores screenshot records and metadata in SQLite for future searches.

Source

Detect exact duplicates: Uses SHA-256 hashing to identify identical image files.

Source

I designed the project around local processing rather than a cloud AI API. This makes privacy a core design choice, not an afterthought.

Source