← all articles

private ai on your mac: how on device memory works

there's a reason you'd never install a cloud ai that watches your messages, your browsing and your camera roll, even though it would obviously be useful. the usefulness was never the question. the upload was.

that instinct is right. it's also solvable now. on device ai got good enough that the most useful version of a personal memory tool no longer needs to ship your life to a server. here's how that works on a mac, and more usefully, how to tell whether an app really does it or just says so.

why on device stopped being a compromise

for most of the last decade, local ai meant worse ai. you took a slower, dumber model in exchange for privacy, and most people quietly took the cloud instead.

two things changed that on the mac.

apple silicon. every m series chip ships with a neural engine and unified memory, so the gpu and cpu share one pool instead of copying tensors back and forth. vision work like ocr, reading text out of a screenshot, went from an expensive background job to something that runs continuously without the fan noticing. apple's own vision framework does it on device by default.

and local model tooling grew up. lm studio and ollama turned "run a model on your laptop" from a weekend project into a download. models in the 7b to 30b range run comfortably on a decent mac and are genuinely capable at the job that matters here, which is reading retrieved context and answering from it. that's a much easier task than open ended reasoning, which is why local models punch above their weight in memory apps specifically.

put those together and the maths flips. the private version isn't the worse version anymore.

what actually happens on your mac

here's the pipeline, and where the privacy boundary sits at each step.

capture. the app records the screen. a well built one is selective, grabbing the focused window rather than every pixel of every display, and skipping frames when nothing changed. less data captured is less data to protect. this step is always local. there's no version of screen capture that isn't.

ocr. each frame gets read for text using apple's vision framework on the neural engine. people assume this has to be a cloud call and on a mac it simply isn't. the words come out on your machine.

indexing. extracted text goes into local databases. full text search for exact matches, vector embeddings for meaning based ones. embeddings can be generated locally too. at this point you have a complete searchable memory that has never touched a network.

inference. this is the one honest fork in the road. you ask a question, the app pulls relevant slices of your history and hands them to a language model. if that model is local, through lm studio, the loop closes on your mac. if you'd rather use a frontier cloud model for harder questions, that retrieved context goes out. what matters is that it's your choice, made on purpose, and not a default buried in the architecture.

storage and backup. your archive sits on your disk. if you want it backed up or synced, that should be encrypted and, more importantly, portable to storage you own.

how to audit a privacy claim in ten minutes

marketing pages are unreliable here and the category has a bad habit of absolutism. some practical tests.

ask what the default is, not what's possible. "can run locally" and "runs locally unless you change something" are very different products. check which one you get out of the box.

watch for absolutes. when an app promises that no data whatsoever ever reaches a network, treat that as a yellow flag, not a green one. nearly every real app makes some network calls. sign in, licence checks, crash reporting, update checks. an honest vendor scopes the claim to the thing that actually matters, which is your captured memory. vagueness in the direction of "totally private" usually means nobody thought carefully about where the boundary is.

find out who holds the keys. encrypted at rest means nothing if the provider holds the key. ask whether encryption is under your key, and whether you can move the whole archive somewhere you control.

check the exit. can you export everything to your own storage? that's the best single proxy for whether a company thinks of your memory as yours. it's also the practical lesson of the past year. rewind ai, which defined this category, stopped recording for good in december 2025 after its company was acquired. anyone who couldn't take their archive elsewhere didn't have a memory. they had a subscription.

read for two separate promises. "we don't sell your data" and "we don't train on your data" are different sentences. you want both, explicitly.

check what the ai can reach. an agent with unrestricted filesystem access is a different risk from one whose access is read only and scoped through a defined set of tools. ask which it is.

where remynd draws the line

we built remynd around this exact boundary, and we'd rather state it precisely than impressively.

capture and ocr run on your mac, on device, by default. your archive is stored locally by default. point the ai at a local model through lm studio and answering happens on your machine too, or use a cloud model when you want more reasoning power, as a choice you make.

cloud backup exists and is entirely optional. when you use it, it's encrypted and you can export it to your own s3 bucket at any time. that's the promise we're comfortable making in public: your memory is never in our cloud, it's in your bucket, with your keys, portable, never pooled, never trained on, never sold.

the agent's access to your data is read only and scoped through typed tools rather than free rein over your disk.

and the footnote we'd rather you hear from us than find in little snitch: like any mac app, remynd talks to the network for account sign in and crash reporting. that isn't your memory. but you should know it.

the point

privacy in this category isn't a feature you bolt on at the end. it's a decision about where the data lives, made once, at the architecture level, and everything else follows from it. an app that captures your entire working life should be one you'd be comfortable running even if you didn't trust the company that made it.

that's the bar. worth holding tools to it.

download remynd free for mac → on device capture and ocr. bring your own model. your bucket, your keys.