MeMex
A private, searchable memory for your Mac
Start new thread

MeMex - A private, searchable memory for your Mac

by•
MeMex gives your Mac a private visual memory. It turns screen activity into an organized timeline of real work moments, then lets you ask plain-English questions and return to matching screen evidence. Daily and weekly reports summarize work you already did, while Pattern Insights spots repeated workflows worth automating. Recordings stay local in a location you control; AI analysis is optional and uses your own provider or compatible local endpoint.

Add a comment

Replies

Best
Maker
đź“Ś
Hi Product Hunt, I built MeMex because I kept running into the same frustrating moment: "I know I saw it. I know I worked on it. But where was it, and what exactly did I do?" Modern work is scattered across browsers, editors, documents, terminals, and chats. Bookmarks only save what we remember to bookmark. Notes only capture what we stop to write down. Screenshot folders quickly become another place we have to search. MeMex gives your Mac a private visual memory instead. It turns screen activity into an organized timeline of real work moments, including when they happened, which apps were involved, and what the activity was about. From there, you can: - Return to a moment without manually organizing screenshots. - Ask questions such as "What did I fix before shipping?" - Get answers connected to replayable screen evidence. - Generate daily and weekly reports from the work already captured. - Discover repeated work patterns and turn them into reusable AI or agent playbooks. Privacy was not something I wanted to bolt on later. Recordings are stored locally in a location you control. AI analysis is optional and uses a provider or compatible local model that you configure. Before data is shared for third-party AI analysis, MeMex explains what will be sent and asks for permission. MeMex is available for macOS as a one-time USD 19.99 purchase. I would especially love feedback on one question: where do you lose work context most often today? Thank you for taking a look.

Comes in handy when I can't remember which file I had open two hours ago, just ask it in plain English and it pulls up the right window. Love that the recordings stay local by default.

Maker

 Thanks “Which file or window did I have open earlier?” is one of the everyday memory gaps I wanted MeMex to solve. The recordings stay on your Mac by default, while AI features remain optional and user-configured.

The timeline view is genuinely useful for finding that one thing I worked on last Tuesday without digging through screenshots. Local-only storage is a nice touch too, makes it feel less invasive than other activity trackers I have tried.

Maker

 Thanks Ensar! That “I know I worked on it last Tuesday, but where was it?” moment is exactly why I built MeMex. I’m especially glad the local-first approach makes it feel less invasive.

How does the local storage hold up over time, like does it balloon fast on a normal workday and need manual cleanup or does it handle that itself?

Maker

 Good question. It doesn’t grow without bounds by default.

MeMex has separate configurable storage caps for raw recordings and processed timeline media, both set to 10 GB by default. It checks storage on launch and every hour, then automatically removes the oldest media when a limit is exceeded. Recent raw recordings are protected for three days, and the searchable timeline-card text remains available after older media is removed.

You can view usage in Settings and set each limit from 1–20 GB, or choose unlimited. So routine use shouldn’t require manual cleanup, although daily growth naturally depends on recording time and display resolution.

The timeline view actually made my scattered work day feel coherent, and being able to ask "what was that thing I saw yesterday" in plain English saved me a real hunt through screenshots.

Maker

Thanks Ali! That is exactly the feeling I hoped the timeline would create: not just a pile of captures, but a coherent thread through a fragmented day. “What was that thing I saw yesterday?” is also one of the most natural questions for MeMex. I’m glad it saved you the screenshot hunt. Was the matching evidence easy to recognize once MeMex surfaced it?

tried it for an afternoon and the timeline view feels genuinely useful, scrolling back to find that one design file i lost track of. like that the recordings stay on my machine by default.

Maker

Thanks Sinem! That “one design file I lost track of” moment is exactly the kind of context gap MeMex is meant to close. I wanted the timeline to feel like continuity, not another folder full of screenshots. I’m glad the local recording model felt right too. When you found the file, did you get there by scrolling the timeline or by asking the Assistant? That distinction would help me decide which retrieval path to improve first.

the local-only storage with optional AI processing is a really thoughtful split, it means you actually own your screen history without locking yourself out of useful analysis. nice to see a tool that respects privacy without gutting the feature set.

Maker

Thanks Pınar! That balance is exactly the design principle: screen history should remain a user-owned local library, while analysis is an explicit layer you can add, change, or remove. Recording and timeline browsing still work without AI. A compatible local endpoint can keep the processing local; a hosted provider is optional and receives the disclosed analysis data only after consent. I’m glad that tradeoff came through. Would you personally lean toward a local model, or a hosted provider for better model quality?

the "recordings stay local, AI analysis is optional and uses your own provider" split is the interesting design decision here. if someone plugs in a remote provider (say a hosted API instead of a local endpoint) to ask a plain-english question, does the relevant screen evidence get sent up to that provider to answer it, or does it stay local and only the extracted text/metadata leaves the machine? for a tool whose whole pitch is private visual memory of everything you do, that's the detail that actually determines whether it's private by default or private-if-you-configure-it-carefully.

Maker

 Thanks ! Let me explain this. The current behavior is:

  • Raw recordings remain on the Mac and are never uploaded as complete video files.

  • If a remote AI provider is enabled, MeMex sends selected sampled frames directly to that configured endpoint when generating analyzed timeline cards. This only happens after the user reviews and accepts the data-sharing disclosure.

  • For a plain-English question, retrieval happens locally. The Q&A request sends the question plus text from the matched timeline cards, such as titles, summaries, observations, timestamps, and app/site context. It does not send the underlying screenshots or video again for that question.

  • Requests go directly from the Mac to the user’s chosen provider. MeMex does not proxy or store them on a MeMex backend.
    So with a hosted provider, the accurate description is local storage with optional remote AI processing, not end-to-end local processing. Users who want the entire pipeline to remain local can connect a local OpenAI-compatible endpoint, and recording/timeline browsing still work without enabling AI at all.



    This is a useful callout. Raw recordings stay local. AI processing runs through the model endpoint you choose.

The "You did the work. But the details? Already gone." message really resonated with me. I think forgetting context is a much bigger problem than people realize. Turning work history into something searchable feels like a very natural direction. Congrats and good luck today! đź‘Ź
Maker

 Thank you, Lyra! That line came directly from my own frustration: I could remember completing the work, but not the path, sources, or decisions behind it.

MeMex is meant to make that context recoverable without requiring you to document everything manually. What kind of context do you find yourself losing most often: tabs and files, past decisions, or troubleshooting steps?

How does the search actually work under the hood, does it index OCR text locally or rely on screenshots only when you query?

Maker

Great question. Search is local and text-first; MeMex does not reopen or upload screenshots when you ask a question. During analysis, sampled frames are converted into structured timeline cards with titles, summaries, detailed observations, app/site context, and timestamps, and those fields are stored in the local SQLite library. When you ask something, MeMex parses the terms and time context locally, ranks matching cards and observations locally, then sends only the top matched text and metadata to the configured model to compose the answer. The current build does not maintain a separate full OCR index. Visual analysis happens when cards are generated, not at query time. If the configured provider is hosted, selected frames may be sent to it during that earlier analysis step; the Q&A request itself does not include screenshots or video.

12
Next