TheYahiaBakour

oh thanks for this :)

let me know how everything goes with the integration over email, always down to help

firecrawl doesn't have a search index, we're probably closest to them at the moment tavily, exa, parallel, you = search index for ai cloudflare's browser offerings are not the best in terms of quality, at-least from our testing + anecdotal reports

anything specific you want me to compare across these companies? to outsiders they look the same but it's actually quite a diverse lineup you've asked about

maybe i'm just telling the truth: https://www.context.dev/customers

fixed & deployed, thanks for flagging.

thank you!

is that a problem/annoying? i thought it would be fine

i too would have had this view before i started the business, however it's actually really hard, additionally teams migrate to us from in-house solutions all the time

i think about this too, perhaps you're right, if (big if) the web was designed with the end goal in place, however it was a series of ~interesting~ mistakes & decisions that led to where we are today

the same could be said of most cybersecurity companies too

i've yapped quite a bit in this thread already about my journey, but happy to provide any (hopefully useful) insights, you can DM me on X, mention this comment please: https://x.com/mynameisyahia

the reality is that the space is huge and expanding

many that you mentioned serve different needs and it tends to not be zero sum to everyone's surprise (including mine at first)

e.g.

browseruse, browserbase = browser automation exa, parallel = search for ai (primarily)

we differentiate by prioritizing the infrastructure use-case, we encourage people to build products & features on top of our APIs and build it accordingly

some direct differentiators are: no hidden credit multipliers, world class brand data, and an api that just works

we're trying to be good samaritans on the web, and cache data whenever possible so we can avoid overloading a website, it's the main reason we don't offer "login with ai" features even though it's trivial at this point, it's quite hard to figure out how to avoid shady behavior while building something people want, i don't have a good answer yet and neither do many others

lastly, to reiterate, lots of our customers migrate from alternatives, but lots also just use multiple providers

i see you too are an experienced dev

touché

"the first 90% of the code accounts for the first 90% of the development time. The remaining 10% of the code accounts for the other 90% of the development time."

now for my actual thoughts, if that works for anyone in production reliably, then they should at-least try to do that.

many of my customers moved from in-house solutions because the engineering time spent on maintaining something like this alone makes it quite the undertaking, the infra needed to support something like a few hundred TPS w a browser fleet would cost more than a sub to us in the majority of cases

ignoring the obvious ragebait, the soc 2 "thing" is the truth, we are type 1 certified, and are in observation for type 2

it counts as "reverse engineering" a website which is much worse for the website owner imo, then again im biased

- worst is "extension" based traffic routing where your provider is essentially tricking end users into routing traffic through - opt-in p2p networks can be described as botnets sometimes, i try to avoid these but not as bad - good enough dISP proxies can be classified as residential quality, work quite well, although people have argued w me on their quality - managed business/enterprise residential gateways are ideal, because businesses opt in and allow the traffic - few other options

if it needs auth, we don't do any type of logins at the moment, still figuring out how to do it without attracting the wrong type of customer (someone doing shady stuff)

popups / cookie banners are quite easy to get through with enough heuristics for 99%+ of cases

content-blockers are the same thing as the auth scenario, hard to figure out where to draw the line between building something people want and doing something shady

thank you, im not sure who this is though, but please email me if i can help in any way

ty, it's here! https://docs.context.dev/install-mcp

100% yes, i found out about that company recently too, it's a tempting idea for sure

you just found my end goal :)

Fascinating, this is definitely a path i was thinking about for a bit but decided against doing it primarily since it changes the business fundamentally

hey, happy you like it, to be honest we had no real secret, it takes a ton of time and effort to earn developer trust

i got my first customer after 1 month, and then just worked like hell to make him happy even though it was a very large company paying me $99/mo at the time, they're still a customer too

since then, i just locked in on every customer until they were thrilled, and once we hit 50, word of mouth started to kick in, now we're at 300+ and get a referral every other day which is awesome

i think our community appreciates effort, and when someone goes the extra mile to make sure your problems are solved, you tend to remember that. it doesn't scale super well, but you'd be surprised how far it'll take you

hi, no worries at all, it came off perfectly fine

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

will let my designer know, it's a dev-focused product, and we're all so finely tuned to avoid slop, so design & feel was really important

happy you noticed that, i put quite a bit of love into the ui, i've found engineers care alot about polish & feel of the webapps they use, even for an api product

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)

im not sure if grok is on here, i think that's an X thing

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

thank you, i try to ship updates often: https://docs.context.dev/changelog

im not sure the models do this, rather the tooling around them, however web search/extraction by the model providers is ridiculously expensive and quite slow, so going into production it makes sense to use a provider (like us)

please do, and if you see anything off let me know, we've yet to lose a single "bakeoff", i normally ask customers to just have cc/codex run it so its somewhat unbiased

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!