Mirowl

Search all your screenshots via a local OCR-powered AI

Mac

Productivity

Artificial Intelligence

Visit WebsiteSee on Product Hunt

Native macOS Vision for the OCR instead of a bundled cross platform model is the choice that earns trust here. On device accuracy and a near zero idle footprint are exactly what a menu bar utility lives or dies on, and Rust plus Tauri is the right call for an indexer that has to stay invisible. Read your reply to Joe on the Pro tier visual descriptors. The follow up I would push on: when both layers are available, does a query rank OCR and visual embeddings together, or does OCR run first and visual only kicks in as a fallback? The two paths can disagree, and a screenshot with no text but strong visual content should still be able to outrank a partial OCR match. And on a library of tens of thousands of old screenshots, does the first full index throttle itself, or is the cold start the painful part?

I have, like, thousands of unnamed screenshots just sitting there because once they get buried, it’s basically impossible to find them again.I've never really preferred cloud storage for screenshots/files because of the privacy aspect, so the fact that this works mostly on-device is probably the biggest selling point for me.

Very useful one, as because we take screenshot of ideas, workshops slides and every important thing under the sun that we feel we may need later on. but later on while looking for it never really find them. this will definitely solve that issue. can you make a similar thing for Windows please?

Finally, a tool for the thousands of screenshots I swear I’ll organize “later.” 😅 The local OCR + privacy-first architecture makes this stand out. Looking forward to trying it out!

rust/tauri + native Vision — nice combo. built similar local-first on mac, the OCR pass got memory-heavy past a few thousand shots. you indexing incrementally on new ones or batching the lot?

Awesome... this looks great.. i have some many screenshots and struggle to organize them

I like the local-first approach. Is Mirowl currently macOS-only, or are there plans for a Windows version in the future?

Built a K1 document OCR pipeline professionally and spent the last week generating hundreds of AI video storyboard screenshots across GPT and Kling. The screenshot search problem is real — I was manually scrolling through folders looking for specific reference images. Curious how Mirowl handles images with minimal text — like a cinematic still or a product photo with just a logo. Does the AI understand visual content beyond just OCR, or is it purely text extraction from images?

Nice one @safiullah_mohamed , upvoted :)

When you say local OCR powered AI, how much extra infra would it need to run?

Nice that everything happens on device, as i state with thoth, our devices have more computing power than the Apollo guidance computer so why offload computing to the cloud !

Quick question: does Mirowl rename the files or propose titles based on the content, or is it search-only? Auto-naming "Screen Shot 2026..." into something findable would be huge for me. To keep that local it could be done with apple intelligence

Local OCR is a smart call, especially for screenshots that often have personal stuff in them. Curious which engine you went with under the hood, Apple Vision or something custom? I work with on-device OCR too and the accuracy on dense text was the hardest part to get right.