selves.me
A private journal that quietly builds a living identity portrait from your own words — and, only when you're ready, lets the world read it.
Every tool built to help people express themselves online starts in the wrong place. Substack opens to a blank page and asks you to write a newsletter before you know what you want to say. LinkedIn asks you to describe yourself before you know who you are. Linktree asks you to curate a presence before you have one. The blank public page is the enemy of honest self-articulation. Most people carry the question who am I, really? quietly for years without ever getting closer to an answer.
Invert the whole pattern. Start with a private journal — thirty seconds of voice on the way home, two lines before bed, a photo of something that mattered today. No audience, no performance, no pressure to sound interesting. As entries accumulate, an AI reads everything the user has written and quietly builds a living model of who they actually are: their values, their patterns, the story they're currently in, the gap between what they believe and how they live. Only then — and only if the user wants — does any of it go public, as a living identity portrait written in their own voice.
- Voice-first capture — thirty seconds into a phone, transcribed live with the browser's native speech API, no native app required
- A quiet, sacred journal — photos, voice, text, no likes, no shares, no social primitives of any kind
- Weekly worldview synthesis — Claude Sonnet 3.7 reads the week's captures and reflects back a narrative portrait, grounded in a specific intellectual framework
- A private insight layer where patterns surface without being broadcast
- An opt-in public page at selves.me/username — generated from the user's own words, never filled out like a form, updated automatically as the user grows
React + Vite · deployed on Vercel · installable as a PWA
Supabase — Postgres with RLS, magic-link auth, storage, edge functions
Claude Haiku — capture processing, in-flight enrichment
Claude Sonnet 3.7 — weekly worldview synthesis
Web Speech API — browser-native, no native app, no model hosting
Stripe — gated public-page and premium synthesis
JavaScript / JSX — deliberately not TypeScript while the model is still moving
Selves is the clearest case for taste is the moat. No template could have produced this product — inverting the blank-page pattern was an opinion, not a feature. Every choice, from Web Speech API over a hosted model, to JSX over TypeScript for speed, to the specific narrative framework driving the synthesis, came out of one operator making calls. That's what Barael sells.