Mirowl - Search all your screenshots via a local OCR-powered AI
by•
A frictionless, local-first Mac app to index and search all your screenshots and image assets. Built with Rust/Tauri for zero footprint and powered by native macOS Vision for 10x OCR accuracy. Optional cloud, no tracking—just pure utility.
Replies
Mirowl
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.
Mirowl
@erdembilgin Great question! The accuracy on dense text is definitely the 'final boss' of local OCR.
For Mirowl, I moved entirely to the native Apple Vision framework for the text extraction. In my testing for v1.1.0, it was spot on compared to general models, especially for high-res Retina shots.
For the auto-categorization and tagging, I’m using a local model so that we can keep the entire pipeline on-device.
@safiullah_mohamed Makes sense. Keeping the whole pipeline on-device is the right call for screenshots. Nice work, will keep an eye on Mirowl.
Mirowl
@erdembilgin Thanks, Erdem! You are spot on, privacy is exactly why I started with screenshots.
But I actually designed the engine to be flexible, you can point Mirowl at any folder on your Mac (like project assets, downloads or design archives) and it will index and tag them exactly the same way. The goal is to make all your visual knowledge searchable, no matter where it's stored. Appreciate you following along!
I like the local-first approach. Is Mirowl currently macOS-only, or are there plans for a Windows version in the future?
Mirowl
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.
Mirowl
@diksha_k that buried feeling is exactly what drove me to build this. i have folders with thousands of shots too and the cloud privacy tax was always a dealbreaker for me. glad the on-device focus is hitting the mark for you.
Thoth - Your Private AI Scribe
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
Mirowl
@matthieu_v Love the Apollo Guidance Computer analogy! You’re absolutely right - our local hardware is more than capable of handling these workflows without a 'cloud tax.'
Regarding re-naming, Currently, Mirowl keeps the original file name on your disk to ensure we don't disrupt your existing filing system, but allows you to rename the asset within the app for searchability.
However, auto-naming 'Screen Shot' files is one of my top roadmap items. I’m actually exploring how to leverage Apple Intelligence and local LLMs to do exactly that in the next version. It’s the final step to truly killing the desktop clutter!
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?
Mirowl
SDRx
Mirowl
Mirowl
@deepakgupta23 Great question! We started on Mac because we wanted to leverage the native macOS Vision engine and a Rust core for high-performance, local-first search.
While a mobile version would be cool, we’re currently 100% focused on making the desktop 'Screenshot Graveyard' a thing of the past first. We want to be the best possible tool for the workstation workflow!
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?
Mirowl
@qifengzheng Great point! Memory management is definitely the biggest challenge when you're doing local OCR at scale. For mirowl, I handled this by using the native macOS Vision framework directly through Rust. Since it’s optimised by Apple to use the Neural Engine, the footprint stays surprisingly lean. To keep things stable, I use a native folder watcher to index new shots incrementally, but for larger batches, I built a sequential worker pipe. That way, the app only ever processes one image at a time, which keeps the memory usage flat whether you're indexing 10 images or 1,000. It’s been feeling really snappy so far!
@safiullah_mohamed the one-at-a-time worker pipe is the right call for flat memory — i'd have reached for batching and regretted it. does the watcher ever fall behind on a big import, or does the queue just absorb it?
Mirowl
@qifengzheng Exactly. I kept the discovery and heavy lifting separate to avoid that. The watcher just handles the high-speed 'ingress' - it indexes the file locations in the DB almost instantly and then pushes the IDs into a Rust queue.
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!
Mirowl
@khushi_ranwa Haha, I was exactly the same! 'Later' never comes until you have a way to search it instantly. Really glad the local-first approach resonates with you - privacy was my top priority when developing this. Hope it helps you kill the clutter!