Privy reads your own records on your own hardware — decades of email, texts, contracts, photos, and recordings — and answers your questions in plain English, showing the documents behind every answer.
Request early accessBuilt by an operator and investor who wanted it for his own archive.
Your life is scattered across fifteen apps that were never built to talk to each other. The lease is in Drive. The amendment arrived by email. The contractor's promise is in a text message. The date you agreed it is on your calendar. The photo that proves the damage is in Photos.
So one simple question becomes a hunt. You open four apps, guess at search terms, and try to hold half an answer in your head while you go looking for the rest. Most of the time you give up and go with what you remember.
Fifteen places one answer might be hiding.
Email accounts, message history, cloud drives, photo libraries, voice recordings, notes, calendars. Everything is indexed locally on your machine.
No filenames, no folders, no search operators. Ask the way you would ask a person who knows where everything is.
A straight answer, plus the actual emails, documents, and photos it came from, with dates and sources.
Not a folder of files. The whole archive — searched together, wherever each piece happens to live.
No folders to remember, no filenames to guess, no search box that only matches the exact word you typed.
Type the question the way you would say it out loud. Privy works out where the answer lives.
Email, texts, contracts and legal documents, tax and financial records, photographs, voice recordings, notes and calendars — all searched together.
Each answer points at the message, file or photo it came from, so you can open it and check for yourself.
Telling an executed document apart from the drafts before it when nothing in the filename says so. Not available yet — we will say so here when it is.
Find pictures by who is in them and where they were taken, without ever having named a single file.
New mail, new files and new photos are picked up on their own. There is nothing to re-import.
Most AI tools get useful by taking a copy of everything you have. Privy is built the other way around.
Your mail, files, photos and recordings sit on computers you own, in your home or office. Privy reads them there.
When a question does need a cloud AI to help with the wording, names, account numbers and similar details are swapped for placeholders first. The outside model sees the shape of the question, not the people in it.
The real names and figures are filled back in on your own screen, after your fingerprint. They are never sent back out.
Removing something from Privy removes it. It does not reappear later in an answer.
Copies are kept and restores are tested, so a failed drive is an inconvenience rather than the end of your archive.
Illustration. Fictional example.
Your archive is indexed and searched on a machine you own. There is no copy of your life on our servers.
Every answer cites the real documents, so you can verify instead of trust.
Sensitive details are protected before anything optional ever leaves your machine, and the most sensitive never do.
Nothing leaves the building.
Decades of records scattered everywhere — email, text messages, contracts and legal documents, tax and financial records, photographs, voice recordings, notes, and calendars — spread across old machines and services, with no way to ask a simple question about any of it. The tools that could answer wanted it all uploaded to their cloud first. Our founder, an operator and investor rather than a programmer, decided that wasn't a trade worth making. So he built the thing he wanted: Privy reads everything on his own hardware, answers in plain English, and shows the actual emails and documents behind every answer. Nothing leaves the building. Privy started as one man's archive. It's now available to yours.