Service exampleOpen SourceOpen source
OpenBrain
Capture reels, posts, links, and screenshots you save. OpenBrain reads, summarizes, and lets you find them in plain language.

Result
Plain-language search over everything saved
The problem
Everything you save gets saved somewhere you will never look again. Bookmarks, saved reels, screenshots: all of it is write-only.
What I built
Built capture for the places things actually get saved (the web, the Android share sheet, and a Telegram bot) and an ingest pipeline that reads each item on the way in: OCR for screenshots, extraction for pages, then a summary, tags, and an embedding so it can be searched by meaning.
The outcome
You can ask for the thing you half-remember saving and actually get it back. Self-hostable, so the archive stays yours.
How it works
- 01
An item is saved from the web, the Android share sheet, or the Telegram bot: a link, a screenshot, a reel, a post.
- 02
It is read on the way in, not on the way out: OCR for screenshots, extraction for pages and posts.
- 03
The extracted text is summarised and embedded, so the item is searchable by what it was about rather than by its filename.
- 04
Retrieval answers a half-remembered description instead of requiring the exact words it contained.
The AI layer
OCR at ingest, summarisation and tagging for a readable record, and hybrid keyword plus semantic search, so an item is found by its exact words or by what it was about. Doing the expensive reading once at write time is what makes search cheap at read time.
The engineering layer
Every capture is written to an immutable log before processing, so an item that fails to parse is never dropped. Around that: a vector store, an AGPL-3.0 licence, and a deployment shape simple enough that self-hosting is realistic rather than theoretical.
Key technical decisions
Read at ingest, not at query time.
Processing on the way in costs more once and makes every later search fast. Processing on the way out means every query pays for OCR again.
Self-hostable, because of what people save.
A personal archive is the last thing anyone should be asked to hand to a third party. Self-hosting is the feature, not a deployment option.