https://www.makralabs.org/about
I have been working on this problem for 6 months.Makra brings down the cost of web scraping by quite a lot, using novel memory and layout caching mechanisms.Currently it's web scraping, but the same can be applied with all kinds of Browser-use application.Let me know what you think.And, just FYI: benchmarks will be public soon. We're on it.
This is the first version that’s out. And soon, we’ll be adding independent benchmarks.
The plan is to build something as solid as Firecrawl, but more efficient.
https://www.makralabs.org/about
The goal was to bring down the cost at the context eng. level. We do it with Layout Memoization.Instead of dumping HTML into the context window, we have built a continual learning browser harness (read only for now).We have built an early prototype for you to try out, where you can:1. Spins up a browser instance 2. Extract any structured or tabular data from anywhere on the open-web 3. And you...