Here’s a demo video: https://www.tella.tv/video/build-faster-with-context-dev-api...
Since it’s an API, here are the docs: https://docs.context.dev/quickstart.
You can send us a URL and get back clean Markdown, rendered HTML, screenshots, extracted images, etc.. You can also send us a domain and get company or brand context: name, description, logos, colors, fonts, social links, screenshots, style information, and related metadata. For more custom use cases, you can send a URL plus a JSON Schema and ask us to extract structured data from the site into that shape. For example, you might ask for pricing plans, product categories, office locations, support links, integration partners, or anything else that is visible on the public site.
The goal is to give developers the output they actually want. Raw HTML is rarely the useful thing; the useful thing is usually Markdown for a model, JSON for an application, a logo for a UI, or a structured company profile for an agent.
Before, I worked at Amazon and Sunrun, and co-founded StockAlarm.io & essense.io, both of which were acquired. Also, I built knifegeek.io, which scraped pocket knives from across the internet and listed them easily. The project is outdated now (coming back soon) but back then it hit the frontpage of hacker news and people seemed to like it: https://news.ycombinator.com/item?id=34604281.
Just before Context.dev, I built Brand.dev. The idea was that your software product should automatically know about your customer if they sign up with a corporate email. The API pulled brand data such as logos, backdrops, name, description, industry, and more from the public web and surfaced it to your product to integrate as part of their onboarding experience. That’s worth doing because conversion rates on onboarding improve dramatically when you go from “enter all this info” to “confirm all this info” (and there was never any privacy concern all the information is public).
That was a nifty niche, but the more customers used it, it became obvious that “brand data” was only one slice of a larger need. People started asking for things like screenshots, structured extraction, and LLM ready data. So I expanded to Context.dev, and applied to YC (got rejected after an interview), then kept going and re-applied at which point I got in as a solo founder.
People use Context.dev in more ways than I can list, but here are some: keeping context up to date on customer websites for chatbots - building beautiful brand assets/ads for customers - enrichment flows using agent harnesses like eve.dev - crawling customer websites into chatbot knowledge bases - turning GitHub repos into branded docs sites - academic journal and PDF crawling. There are a ton more examples at https://www.context.dev/customers.
We know that many crawlers are not behaving like good citizens on the web, and the entire space has a bad reputation as a result. At the same time, customers are not usually trying to buy “scraping”. They are trying to make a support bot work, personalize onboarding, enrich CRM records, generate docs, monitor leads, or let an agent research a company. There are lots of legit use cases. We want to satisfy those while being respectful of everyone involved.
We maintain a caching layer and avoid hammering websites. Customers can configure the cache, but if we find we’re sending too many requests to a url in a certain amount of time, we step in and tone it down. Websites can opt out of our service, and we respect these requests and add them to our block list.
We focus on customers who want to build cool things for their users. Enriching onboarding is a popular use case. So is integrating context about their own websites (things like support bots), and building agents that can automatically reason about complex tasks involving the internet.
We only allow customers to use brand data to identify a specific customer on their software, you cannot use it in your own materials or to imply endorsement.
I'd love to hear your feedback about the product in the comments, thanks!
Discussion (29 Comments)Read Original on HackerNews
EG if I start passing in Linkedin pages what is your expectation of the result that people would see per profile.
EDIT:
Congrats on the launch seriously hard work, just wanting to understand your scraping stance more. I've worked with a lot of tools on this, didn't mean for my initial comment to be adversarial.
yes, we use residential proxies + all requests go are js-rendered, we maintain a caching layer which is 95%+ opted into by customers
it's all included in the credit price, great value compared to alternatives, the business model does rely on scale and our margin gets better the more requests we serve (esp infra cost for k8 + browser fleet)
to answer your e.g., yes public linkedin pages will work fine, anything behind a login we don't really support out of the box until we can figure out a safe way to do so, since that's where red lines are drawn
we step in whenever we see our service is hitting a website more than it should, this usually means reaching out to a customer for clarity on why they are not opting into the cache, we have alot of safeguards around fraud/spam and will let someone know if their request pattern looks like they're causing harm
Agents need clean/current context from the web, and this is the best way I’ve found to give it to them. The internet is clearly moving in this direction: companies are starting to realize their sites need to be legible to agents. Some are already adapting but many haven’t yet. Context feels like an important part of that transition
Yahia is a great builder. His pace of expansion has been impressive, excited to see where he takes Context.
brand data is a shockingly hard problem to get right
> When Should I talk to sales? > Talk to sales if you need high-volume pricing beyond 2M credits/month, custom rate limits, SSO / SAML, SCIM provisioning, an uptime SLA, annual invoicing, an MSA / DPA, or a dedicated support channel. Reach us at hello@context.dev or through the contact page.
Would that this were the norm everywhere, rather than (say) a sales rep from Datadog scraping my phone number from who knows where to ask about my company's needs after I sign up for a free account on a whim :)
i'm an engineer by trade, and always hated things like forcing a sales call, or having hidden credit multipliers, i tried to build this with the same ethos i like for my own dependencies (shoutout axiom.co)
I am interested in KnifeGeek though - looking for a good OTF (ultratech?)
If you want differences as of right now
- 1 credit = 1 scrape, no hidden credit multiplier - we have world class brand data - we're focused primarily on the infra use-case, rather than gtm & everything else - anecdotally, customers have seen their error rates drop quite dramatically
In general it's a huge space, firecrawl is a wonderful company, it's fun to compete with them, planning to add more things soon which should make the differences clear
Thanks for the quick response - and always happy to see more competition in the space. Best of luck with future features!
on the 2nd point, most industries are not zero-sum, and many of customers use multiple data providers in any case, so agree with you there
thank you!
in terms of llms.txt, we're not primarily an AI product (although some features do use LLMs), and speaking to friends who run products it seems to be not very helpful, even though we have one as well, i didn't see it move the needle much
even my own coding agents don't look at llms.txt when looking at our own website, so unsure of whether that standard will survive the test of time
shipping a bunch of new things soon which should make it clearer, but as of today yeah
AKA unusable for high value data.
also, while it might seem expensive, we're cheaper than every other option out there, because there's no hidden credit multipliers. every single customer who uses us halved their bill + error rate
but if you were to ask me, we're more fully featured than cloudflare, and anecdotally a ton more reliable in terms of error rates. back when it was brand.dev, i actually tried to use cloudflare's apis and it was quite unreliable, so we built our own stack instead