# Backscroll

> Agent that scrolls your feeds

Published: 2026/05/21 • Author: Surya Dantuluri • Canonical: https://sdan.net/projects/backscroll

Backscroll is an agent that scrolls your feeds. It scrapes my twitter and instagrams feeds and imports as much historical likes and bookmarks to send to a llm to compile a feed that you really want to see.

![Backscroll native UI](/projects/backscroll-native.png)

The algorithm I've made for myself is reminiscent of [Thunder and Pheonix](https://github.com/xai-org/x-algorithm) and includes a mixer that is based on a dozen rubrics that every tweet/post gets scored against. This rubric I set initially and then evolved over time as I've labeled tweets and posts that I like or dislike with the option to also add commentary. Luckily LLMs have gotten much cheaper and a lot more intelligent so even if its scrolling both twitter and instagram feeds at 0.15mph 24/7 it would cost less than $50/week.

![Live scrape log inside the Settings panel — one run logged 81 new tweets in 69.8s, with browser-launched / surface-loaded / Tweets-visible / Scrolling-done timestamps](/projects/backscroll-scrape-log.png)

![Settings status panel — Browser run 0/120, scrape / following / discover / bookmark / likes jobs all succeeded, corpus tree window-12h-10000 showing 2,929 tweets · cap 10,000 · ~274k tok](/projects/backscroll-settings.png)

::media(/projects/backscroll-demo.mp4)

![Backscroll Twitter-web frontend](/projects/backscroll-twitter-web.png)

![Feed directive](/projects/backscroll-directive.png)

![Backscroll News — HN-style frontend](/projects/backscroll-hn.png)

![Telegram feedback loop](/projects/backscroll-telegram.png)

This is a in-progress project and I'm still trying to figure out how it works. So far I use it 40m+ a day and it has saved me a lot of time.

I'm working on a denser explanation of this project. Stay tuned!