131–140 of 172 posts
Similar project for macOS which is also open source: https://rem.ing https://github.com/jasonjmcghee/rem Previously submitted on HN by the dev with some decent discussion 3 months ago here: https://news.ycombinator.com/item?id=38787892
Earlier quoted context omitted.
rewind.ai is another example of this, but their recent pivot into cloud only storage for this and renaming to limitless.ai makes me glad that open source stuff like this popping up so you are not forced into a cloud storage situation. And I say this as a paying customer who will probably stop being one.
they also seem to have shifted to hardware/"AI" wearables (lavalier mics?). hardware is not a promising shift imho
> Please refresh and try again or.
We built in almost 2 decades ago now (including the ability to scrub to a point in the past and resume execution from there) http://www.cs.columbia.edu/~orenl/papers/sosp07-dejaview.pdf Abstract: As users interact with the world and their peers through their computers, it is becoming important to archive and later search the information that they have viewed. We present DejaView, a personal virtual computer recorder…
Great project name!
Similar project for macOS which is also open source: https://rem.ing https://github.com/jasonjmcghee/rem Previously submitted on HN by the dev with some decent discussion 3 months ago here: https://news.ycombinator.com/item?id=38787892
also http://rewind.ai which is a company doing the same thing
Amazing that this was done by a non-professional dev. Huge cudos. (Tbh why not become a professional dev? You clearly have the skill and at least some interest.) There's a huge miss in this implementation though: 95% of the time what is on screen is web-browsing. So to go from nicely formatted markup with title tags -> video -> OCR is clearly missing am ore obvious path (either a proxy or browser extension).
And yes, most of my screen time is also web-browsing. Currently, I can use the web page's Windows title as a reference, which provides quite a bit of information. To enhance this feature, it might consider using like Chromedriver to gather more details, such as web links and page text, similar to what 'Rewind' offers.
Has anyone built something like this using accessibility APIs instead of (or in addition to) OCR? It seems like a waste to OCR everything when you could just get the text directly from the accessibility APIs. Also seems like potentially a good way to connect LLMs to UIs, and something like this would be the way to collect the training data.
I concluded that in case this is a viable approach, Microsoft or Apple will built that into their OS natively as part of a copilot that remembers everything and comes to assist the user with the knowlede.
My screen history was not as advanced as the app mentioned here though. And I didn't use it myself.