[dthcst]

Same reason here: I got tired of my stuff living on someone else's server, so I ended up building my own local memory thing. Not a developer at all, just stubborn.

Two honest questions, since you built it for yourself first:

1. Are the entries plain files I can open and read without your app, or a database? For me that ended up being the whole point. If I can't read it without you, it's not really mine.

2. You say everything is on device, but inference goes to a zero-retention endpoint. Have you looked at running a small local model for the AI part? "Private" and "my text leaves the machine" are hard to hold together in one sentence.

Not a criticism, I hit the same wall myself. Nice project.

[arisAlexis]

1) the app is using a database stored on your phone. you can export it all in json or llm format. the one is for export/import and the other to feed an LLM with your data to chat more

2) yes I tried it and it becomes so slow it's unworkable right now but in a future version totally possible. Gemma 4 needs an iphone 17 pro or similar to run in a normal timeframe and still it's slow and also the whisper-large is also very slow. it would also need to download some gigs of data. but that was actually the first version I built :)