Show HN: Echologue – the private AI voice journal I built for myself

arisAlexis 29 points 13 comments July 29, 2026
echologue.com · View on Hacker News

I have tried journaling many times but nothing stuck. So I decided to make my own app for myself with these features: * Voice first * Private first * AI chat * Automatic tagging, meaning extraction, and semantic retrieval using embeddings stored locally * Export to LLM the AI angle is especially interesting for me. It allows me to ask questions like: * "remind me highlights and crazy nights in the last 3 months" * "How was I feeling during my trip in Spain and how big of a problem was my breakup" * "How would you judge my overall interactions with Marc after I told him about my problems" the overall process is fire and forget. I just talk for let's say a minute every day or when there was something of interest. Everything is stored on device. The AI inference is done with Zero Data Retention Endpoints. No email or anything else is kept, you are completely anonymous, I have no idea what or how people use this. Otherwise journaling doesn't work. I can't say my secret thoughts when I know someone has a master key or can suffer a security breach. I hope you enjoy the product as much as I do.

Discussion Highlights (8 comments)

parthmule28

I just tried the android application, really like the privacy first approach. Would you consider adding BYOK so that a user could have complete control over where inference happens? I realize it might not fit your architecture, but it seems like a neat optional setting. Either way, neat project.

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.

kingkemol888

Great,maybe a Great Work!

hsoc

I downloaded it today. Pretty cool

steezeburger

I like the idea behind this a lot and feel the same way about my notes. I also built my own app for it and have a very similar feature on the roadmap. Cool stuff!

pluc

Asking an AI how you feel about a person or the highlight of a trip is such an offloading of basic human identity.

dmrivers

Tresor.co or cloud.near.ai could be a useful inference provider for this kind of project as these providers run inference inside enclaves which verifiably cannot peek at your data even as the hypervisor. Both are open source. Tresor.co is EU based so I'm thinking of using tresor.co for one of my projects as I trust EU regulation more for this sort of thing.

totallygeeky

Projects like this are truly baffling to me, the point of journaling is in part the reflection, which you offload to the AI system in this case. You spew what thoughts and feelings you want at it and ask it to tell you how to feel, or how good you did. It kneecaps the precise skills and work needed to become a more whole and thoughtful person, despite wearing the skin of something that might help.

Semantic search powered by Rivestack pgvector
15,380 stories · 143,452 chunks indexed