Context.dev’s full-page screenshot API is now better at capturing scroll-triggered content, video frames, and canvas sections.
Your personal agents should be able to get full-page screenshots without spinning up a browser on your machine.
Let's save that for the elites with 128GB of RAM.
1
22
More product details. Less popup clutter.
We’ve improved Context.dev’s Markdown extraction to skip closed dialogs, clean up product tables, and keep headings where they belong.
Cleaner content for your agents to read, compare, and use.
1
99
Company Search now returns social profile URLs alongside company results, including LinkedIn, X, Instagram, YouTube, and more, when available.
Enrich your CRM, research prospects, or build company directories with fewer follow-up searches.
Customers got weird fonts? We got you. 🧟
Don’t make them rebuild their brand during signup.
Customers use Context.dev to generate branded emails, slide decks, and websites without making users enter their brand details manually.
Less setup. Faster time to value.
Everything is public:
-judge prompts
-historical samples
-full source code
We were inspired by NEEDLE’s live search evals, and brought live evals to scraping with TRACE.
Try it here:
trace.context.dev
Check out the code:
github.com/context-dot-dev/t…
Every day at 00:15 UTC we sample ~2,500 never-before-tested pages across 9 categories and send the exact same set to Context.dev, Keenable, Firecrawl, and Exa.
We measure:
– Useful content rate
– Latency
– Cost per useful page
– Why pages fail
Latest sample (Nov 6): Context.dev 87.0% · Keenable 84.2% · Firecrawl 82.3% · Exa 79.1%
Introducing TRACE: Transparent Real-world Assessment of Content Extraction.
A live benchmark of fresh URLs, updated daily.
Most scraping benchmarks are instantly outdated the day they are released.
To fix this, we mine the web for new URLs every day
Here's how it works ↓
The answer is buried in a 500-page PDF. Your customer shouldn’t have to dig for it.
Context.dev PDF parsing now preserves page numbers in Markdown, so your agent can cite the exact page behind its answer.
Like Yahia’s favorite toppings: pineapple and fresh cheese. 🍕
Batches now supports up to 100,000 URLs.
Index a whole website with one request: get markdown, json, screenshots, images & more.
We handle the queue and per-site concurrency while your job runs in the background.
Set it. Forget it. Get the results.
Context now powers Zero's enrichment infrastructure, keeping information on 20M+ companies fresh.
Zero searches and scrapes millions of data points every day to power its AI CRM, company enrichment, and custom agents.
Learn how they do it:
dub.sh/zero-on-context
3
24
1,241
Introducing Blue Pages, our index of over 80M companies.
Now your agents can find:
-companies with recent funding rounds
-lookalikes for your existing customers
-companies that match a query/criteria
We're already using it internally to accelerate GTM.
Get 500 /company searches free when you sign up to context.dev
It's about time someone rewrote Cheerio in Rust.
Meet Rusteerio, a drop-in replacement for Cheerio.
Rusteerio is:
- 4.5× faster than Cheerio for HTML extraction
- 4× more memory-efficient at 16 CPUs
- Supports async parsing and parallel extraction without blocking the JS main thread
- Passes all 777 Cheerio tests
- Zero npm runtime dependencies
We built Rusteerio to power Context's scraping infrastructure, and it already makes our large, concurrent scraping workloads faster and more memory-efficient (check out our batch scraping API).
Today we're open-sourcing it:
npm i rusteerio











