One API to scrape, enrich, and understand the web. Trusted by 20K+ developers.
Joined May 2024
- Tweets988
- Following334
- Followers4.2K
- Likes869
Pinned Tweet
Every agent deserves accurate and fairly-priced web data, so we raised 9M to make it happen.
To celebrate we're giving away 50k credits to every sign up today.
Let us know what you end up building!
We raised $9M to give your agents the internet.
Led by @generalcatalyst, with @orangecollectv and Robinhood Ventures.
Search, scrape, crawl, monitor with one API trusted by 800+ customers.
We’re making it ridiculously easy to build with web data.
3
22
2,536
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.
ALT Context.dev announces social profiles in Company Search. Find the company. Get its socials. A search for design software companies shows Figma, Canva and Framer with X, Instagram and LinkedIn icons beneath each company. POST https://api.context.dev/v1/company/search.
Context.dev retweeted
Kevin’s first biz SlideSpeak was one of our first 30 customers (still live and highly profitable)
Now with Doop he’s again chosen context.dev to power brand kit generation and scraping (customer #834)
It’s very rewarding to see customers choose us repeatedly over time
Everyone check out Doop if you want a banger paper alternative!
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.
ALT Context.dev: Better Font & Style Guide Extraction. Customers got weird fonts? We still got you. A Halloween-themed Frankensite website flows into an extracted style guide showing its gothic font, colors, Enter if you dare button, and haunted landscape image.
Context.dev’s improved font & style guide extraction turns their website into fonts, colors, and design tokens so what you create feels on-brand from the start.
Feed the docs to your agent:
link.context.dev/styleguide-…
138
Context.dev retweeted
Scored my first #1 place on a benchmark working for @getcontextdev
And not done climbing yet
Benchmark (Needle): Correct retrieval of scholar articles
Context.dev retweeted
Great day of building at the @getcontextdev office with @kgoedecke, @oliviersm199, @karatzas_thomas!
Thanks @mynameisyahia and @triekki for having us!
Context.dev retweeted
Thanks to @getcontextdev new users have the option of matching the FermentIQ UI to their brand. It scrapes their logo & info (brewery name, beer brands etc and colors) and offers to match the UI to their brand. Neat!
Context.dev retweeted
context.dev people search + jev is a game changer for gtm
(paid partnership)
(ai generated)
Context.dev retweeted
Co-hosting a chill coworking afternoon at the @getcontextdev office. Thanks for organizing @mynameisyahia!
Context.dev retweeted
Continued working on Connectors page for the dashboard, with every brand logo pulled from @getcontextdev
Context.dev retweeted
sold! switched over to @getcontextdev in a matter of minutes! it’s faster than @firecrawl and they actually allow discounts for devs on monthly plans (found out after the fact it was only annual).
thanks @mynameisyahia for your help!
Context.dev retweeted
we at Nova( @supercodeai) have been using Context for:
- default web search
- deep search for researchers
- pdf parsing
- brand retrieval
- news and more
and it has been the best experience since day one
Context.dev retweeted
Every time a data provider reaches out to me, or an email validator, anything like that, my first response is, "Send me a benchmark."
There is no loyalty. The race is to be the best per task or the cheapest per task, with no in-between
Really appreciate the transparency that Context Dev delivers
Context.dev retweeted
Lets make AI search better
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 ↓
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%
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…
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. 🍕
ALT Context.dev PDF page numbers. Found the answer? Cite the page. A Markdown document states Yahia's favorite pizza toppings are pineapple and fresh mozzarella cheese on page 452. A chat answers with those toppings and cites page 452.
Enable includeNumberedPages to add original page markers to your parsed Markdown. Works with or without OCR.
docs.context.dev/parse/pdfs-…
168