For years I thought I had a documentation problem.
I didn t. I had a retrieval problem.
There are hundreds of hours of strategy sessions, product demos, customer interviews and workshops sitting in folders on my machine. We recorded everything because the conversations mattered.
Then six months later someone would ask:
"Find every wedding kiss shot from the last three years."
"Find the photo of the red car at golden hour."
"Find that screenshot of vertical tab navigation I saved in spring."
"Which interview mentioned pricing pushback?"
"Find me that French Airbnb screenshot, travel docs, foreign tax forms, expat paperwork, German rental contracts."
"I know I wrote this somewhere"
Journalists. Interview audio, source docs, photos. The kind of thing where a reporter has 40 hours of recordings from one investigation.
Researchers / academics. PDFs of papers, lecture recordings, slide decks. "Which image said the sample size was 283?"
Co-built this with @felixvelarde . Quick context on what makes it different from the obvious comparisons:
Your files stay on your machine. The only thing leaving is the embedding call to Gemini, using your own API key. We don't host, process, or see your content.
Where it's surprised me most, video and audio:
"Find the moment in the customer interview where they pushed back on pricing"
"Which slide showed EBIT in the Q3 board recording"
"Find the bit in the family video where dad and grandma were both laughing"
Plus the obvious wins:
The screenshot graveyard everyone has, suddenly searchable by what's in the image
Cross-language: ask a German PDF a question in English
Happy to answer anything technical: RAG pipeline, why Gemini, local-first tradeoffs. 🦮