Pinned Tweet
Crawl the web, like a database query. At the cost of a vector search: makralabs.org
10x more token efficient than any other agentic web crawlers.
State of AI Web Scraping in 2026
75% of the web is dynamic. Basically database records presented in HTML. Built for humans.
For Agents, this problem was solved by:
1. RAG was the first generation (2024)
2. And then, long-context LLMs took it to a completely new level (2025)
Fast-forward to 2026, and we're basically dumping anything and everything into the context windows; taking Nvidia to the moon.
This consists of claws, browser/computer-use, and agentic crawlers, and scrapers. These have made it easier to retrieve data, but the cost has stayed the same. Underneath, these still rely on long-context LLMs.
And, here's where they fall short:
- Cost at scale: for large datasets, cost grows linearly on a per-page basis.
- Hallucinations: LLMs are prone to hallucinations
- Context pollution and prompt injection
Let me now show you what we have built:
3. Memoization-driven Knowledge and Data Retrieval
It's an work-in-progress implementation for a continual learning harness focusing on Browser-use.
Building applications on top of a memoization-engine like Makra solves all 3 of these problems:
- Lower cost at scale: as layouts are memoized, cost comes down to a vector query.
- Makra extracts data like a traditional scraper. So, hallucinations? Theoretically, none.
- Your agentic loop only has to deal with the DOM nodes it's concerned with: More signal, less noise.
We have built an in-house browser harness (read-only for now) that does the following for you:
1. Spins up a browser instance and sets up proxies.
2. Extracts any structured or tabular data from the web for you.
3. And you can do all this at 1/10th the cost of all the other previous generations.
Try out at: makralabs.org
Makra Labs retweeted
I don't know why I used to keep my @ycombinator application videos private. It was stupid. So this time, I decided to talk about it in public.
Here's my YC application video for the W27 batch. Hope y'all like what we're building!
We’ve built a Browser-harness with continual learning for understanding layouts (does read only tasks for now).
Crawl the web, like a database query. At the cost of a vector search: makralabs.org
10x more token efficient than any other agentic web crawlers.
Read our thoughts on this: teapawt.org/ritsource/status/20937…
Replying to @makralabs
@makralabs is live!!
A project created by my senior @DevDotAshu and it's insane...
Do Check Makra and support the initiative with a Star Rating.
#X #Community #BuildInPublic #GoMakra
github.com/makralabs/makra
1
145
Makra Labs retweeted
State of AI Web Scraping in 2026
75% of the web is dynamic. Basically database records presented in HTML. Built for humans.
For Agents, this problem was solved by:
1. RAG was the first generation (2024)
2. And then, long-context LLMs took it to a completely new level (2025)
Fast-forward to 2026, and we're basically dumping anything and everything into the context windows; taking Nvidia to the moon.
This consists of claws, browser/computer-use, and agentic crawlers, and scrapers. These have made it easier to retrieve data, but the cost has stayed the same. Underneath, these still rely on long-context LLMs.
And, here's where they fall short:
- Cost at scale: for large datasets, cost grows linearly on a per-page basis.
- Hallucinations: LLMs are prone to hallucinations
- Context pollution and prompt injection
Let me now show you what we have built:
3. Memoization-driven Knowledge and Data Retrieval
It's an work-in-progress implementation for a continual learning harness focusing on Browser-use.
Building applications on top of a memoization-engine like Makra solves all 3 of these problems:
- Lower cost at scale: as layouts are memoized, cost comes down to a vector query.
- Makra extracts data like a traditional scraper. So, hallucinations? Theoretically, none.
- Your agentic loop only has to deal with the DOM nodes it's concerned with: More signal, less noise.
We have built an in-house browser harness (read-only for now) that does the following for you:
1. Spins up a browser instance and sets up proxies.
2. Extracts any structured or tabular data from the web for you.
3. And you can do all this at 1/10th the cost of all the other previous generations.
Try out at: makralabs.org
makra - v0.0.4 (beta), is now out: github.com/makralabs/makra/t…
npm i makra





