TL;DR

Sift is a personal knowledge base I built over three or four months that ingests anything — URLs, PDFs, bookmarks, web pages, video and audio files — and makes it all searchable by meaning, not just keywords, with awareness of when things were saved. It runs on your own hardware, answers questions using your own saved material as sources, and sits alongside Obsidian rather than replacing it. I've open sourced it at github.com/pablooliva/sift. This post is the story of why it exists, what I learned building it, and what to expect if you clone it.

My Bookmarks Saved Me Money

A few weeks ago, I was designing a multimedia publishing pipeline for this site. I needed voice synthesis and video generation tools, and I had a rough budget in mind, something like $56/month across a few SaaS subscriptions.

Before committing, I searched my Sift knowledge base. It surfaced two ComfyUI integrations I'd bookmarked a week earlier: Qwen3-TTS for local voice cloning and LTX-2.3 for open-source video generation with portrait support. I'd saved them as simple URL bookmarks with short descriptions — the lowest-effort form of ingestion possible.

Those two results shifted the entire pipeline from a paid SaaS stack to a $0 local approach.

I didn't remember saving them. I wouldn't have found them with a keyword search. I wasn't searching for "ComfyUI" or "Qwen3-TTS." I was searching for what they do. Sift understood the meaning of my query and matched it to content I'd barely thought about since bookmarking it.

That's what a working external knowledge base actually does. It surfaces the right information at the right moment, even from content you forgot you saved — especially when that content comes from the sources you've learned to trust.

Continue reading https://pablooliva.de/the-closing-window/introducing-sift/