15 comments

  • jedberg1 周前
    Very interesting. I worry that if I use your cloud, and a lot of other people do, all of your IP addresses will get banned by all the big players. It will definitely be a fun cat and mouse game!

    Related story: Way back in the day, PayPal was just getting started, and decided eBay transactions would be their perfect customer. The only problem is that eBay didn't allow scraping. So they built an entire proxy infrastructure to go around eBay's rules and scrape them.

    It worked. It worked so well, eBay bought PayPal.

    The side effect of this is that I got control of the PayPal proxy infrastructure since I was on the security team for both eBay and PayPal after the acquisition.

    We used that proxy farm to scrape the rest of the web looking for fake eBay sites (because they would block traffic from eBay's IPs) and we had the guys who built it help us build proxy defense for eBay and PayPal.

    So this could work in your favor, if you manage to constantly scrape a large target who might want to buy you. :)

    • huss971 周前
      That honestly sounds so fun! Who better to build your defences than your attackers ahaha

      Tying into your concern, keeping IPs fresh and high quality will definitely be a balancing act as we get bigger. It'd be one today too if we were to try to offer super granular location controls because there's only so many proxies in X state, let alone X city. Currently, we get to aggregate & QA from multiple proxy providers, so our total pool is 300M+ IPs in the US and so far we've had a 99.95% rate of getting a fresh IP address in a session. So so far so good :)

      As for that last point, I guess we'll see what the future has in store for us :P

      • Is it possible to persist an IP address if we supply the proxy credentials?
        • huss972 天前
          yea, thats totally doable with us! The rest just depends on your proxy and whether it's rotating or persistent.

          With our proxy service this is built for at least the length of a session (up to 24 hours).

      • ProofHouse2 天前
        you might have a captcha issue on your discord haha or something, I cannot join
        • huss972 天前
          well that's ironic ahaha just removed that for the time being, so hopefully you're good :)
      • asah2 天前
        +1 to residential proxy providers like joinmassive.com ! #proudinvestor
        • huss972 天前
          Looks sweet, we'll check em out!
    • j452 天前
      It appears you can set your own proxies to not use their cloud.
  • huss971 周前
    Hello Hacker News! We’re Nas and Huss, co-founders of steel.dev (http://steel.dev). Steel is an open-source browser API for AI agents and apps. We make it easy for AI devs to build browser automation into their products without getting flagged as a bot or worrying about browser infra.

    over the last year or so, we’ve built quite a few AI apps that interact with the web and noticed - a. it was magical when you could get an llm to use the web and it worked and b. our browser infra was the source of 80% of our development time. Maintaining our browser infrastructure became its own engineering challenge - keeping browser pools healthy, managing session states and cookies, rotating proxies, handling CAPTCHA solving, and ensuring clean process termination. We got really good at running browser infrastructure at scale, but maintaining it was still stealing time away from building our actual products. So we wanted to build the product we wish we had.

    Steel allows you to run any automation logic on our hosted instances of chromium. When you start a dedicated browser session you get stealth, proxies, and captcha solving out of the box. We do this by exposing websocket and http endpoints so you can connect to these instances with puppeteer, playwright, selenium(in beta), or raw CDP commands if you’re built like that.

    Behind the scenes, we host several browser instances and route incoming connection requests to one of these instances. Our core design principle was to allow for every session to have its own dedicated browser instance + resources (currently 2gb vram and 2gb vcpu) while still allowing for quick session creation/connection times. Our first thought was to have separate nodes running in a Kubernetes cluster, but the cost of hosting warm browser instances would be expensive (which would be reflected in the pricing), and the boot times would be too slow to handle the scale that some customers required. We got around this by deploying our browser instance image on a firecracker VM, taking advantage of the lightning-fast boot times and ability to share a root FS.

    Today, we’re open-sourcing the code for the steel browser instance, with plans to open-source the orchestration layer soon. With the open-source repo, you get backwards compatibility with our node/python SDKs, a lighter version of our session viewer, and most of the features that come with Steel Cloud. You can run this locally to test Steel out at an individual session level or one-click deploy to render/railway to run remotely.

    We're really happy we get to show this to you all, thank you for reading about it! Please let us know your thoughts and questions in the comments.

    • overu5891 周前
      Very interesting. I’m not sure I immediately see your application either however I have been having similar thoughts.

      After playing a popular indi game (Kenshi) I was wondering about the very simple automation interface the game relies upon. Why not a virtual world (with interfaces attaching any external source) in which business logic agents interact through the available interfaces of the environment, and other agents. Though tbh, I imagine the entire environment as implemented in layers of YAML style schemas and profiles. So all data, whether in a datastore, active instance, streamed or serialized can be related to in the same way. An envelope with attributes and content specified by the type attribute. The only code would then be the rendering environment, and whatever these agents call for stream processing.

      Sort of a gamification of automation, though what can’t be beat is dead simple account of what any one thing is doing at a given time.

      • ohthatsnas1 周前
        Hey, Nas here.

        The concept of agents running wild with only schemas of how to interact with their environment + one another is something I’ve thought about a lot. With current models, I guess this would just be function calling or forced JSON outputs, but I think it would make for some very interesting results.

        With Steel, we’re really just providing a way to do something similar to the “rendering engine” in this scenario but with the web. So agents can interface with their environments (websites) very easily and at scale (which comes with its own difficulties wrt deloying/managing)

    • Would love to read an engineering blog about your journey from trying to run this on Kubernetes and ending up on Firecracker VM.
      • ohthatsnas2 天前
        Haha, would love to write one. Will get started on a draft once I get the time. :)
    • Oras1 周前
      If these instances are shared, how do you segregate login details, sessions cookies, …etc? Are you always running them in incognito?
      • ohthatsnas1 周前
        Instances are not shared. :) Everyone gets a dedicated session with dedicated resources. One session for every machine.
  • orliesaurus2 天前
    Is this very different from https://github.com/browserbase/stagehand
  • capiki2 天前
    Can you say more about your product plans? It looks like this is directly competing with Browserbase — how will you differentiate? Looking forward to seeing how the product and company grows
    • huss972 天前
      Our end goal is to build the LLM OS. We think the best place to start is the hardest but most hairy problem - getting agents to use an internet design for humans on our behalf. So, as we go, we want to keep building towards relieving blockers by handling auth securely, translating webpages, and creating the right toolset for driving sessions. And we want to do this in an open-source and communal way. That's also why we're attacking it bottom-up with infra, so we can build a community of people much smarter than us around getting there. Join the discord if you want to stay on top of our journey :)
  • gregpr071 天前
    Nice!! We are working on a higher level library over at https://github.com/gregpr07/browser-use.
    • huss9720 小时前
      Looks awesome! DM'd :)
  • DanielKehoe2 天前
    Happy to see there's a way to get browser automation for AI without building infrastructure to support it. Yet I don't see examples of connecting an LLM to drive a web session, just examples of using Puppeteer or Playwright or Selenium to drive a web session. Presumably your user base knows how to write custom code for an interface between Claude or OpenAI API and Puppeteer/Playwright/Selenium. Sadly, I don't know how to do that. Would it be fair to expect your documentation to help? What would you suggest to get started?

    Is the interface between Steel, or Puppeteer/Playwright/Selenium, something that might be implemented in the new Anthropic Model Context Protocol, so there's less custom code required?

    • ohthatsnas2 天前
      Good point! The space is so early, and it's 100% on us to help people get started building web agents. We're actually re-working this repo (+ a tutorial with it): https://github.com/steel-dev/claude-browser - which implements a web agent by reworking the claude computer use repo + page screenshots for vision.

      We also have more AI-specific examples, tutorials, and an MCP server coming out really soon (like really soon).

      You can keep an eye out on our releases on discord/twitter where we'll be posting a bunch of these example repos.

    • pkiv2 天前
      I’d recommend checking out Stagehand if you want to use something that’s more AI first! It’s like the AI powered successor to playwright: https://github.com/browserbase/stagehand

      (I am one of the authors!)

  • I don't understand what problem you're solving that puppeteer doesn't already solve.
    • huss971 周前
      We love Puppeteer and use it to power our API!

      We don't compete with Puppeteer/Playwright/Selenium but we're focused on solving the problem of hosting Chromium browsers in the cloud.

      The workflow jump we've seen ourselves and from customers is that it's pretty straightforward to build these scripts locally, but the moment you want to run them in prod, you now need to deal with a ton of overhead around packaging up to docker, resource management, scaling, etc. We want to make that trivial :)

      • I have never had any issues running puppeteer on a server, what problems are you solving that would arise?
        • huss971 周前
          Yeah, that’s totally fair! Not everybody will. In our experience, the problems we solve are the creeping kind that develop over time and show themselves as maintenance costs.

          Let’s say we want to add web automation to our app, and we've set up a single instance of Chrome hosted on a server somewhere that we connect to and drive with Puppeteer. Great, now we need to ensure incoming requests/sessions are managed properly (>1 active session). If we have a ton of active requests, this becomes annoying because now the resources on our server are being eaten up — so we would need to scale horizontally (or vertically) but now that comes with potential downtime and cold start issues. If we decide to keep this instance of Chrome running 24/7 then we need to bake in resource management to handle memory leaks and connection issues. If we don’t keep them alive, then this comes with significant cold start times (10s+).

          Now, let’s say we want to support a real-time scraping use case that requires multiple browsers in parallel. At this point, we would need to use something like Kubernetes with warm pods or maybe lambdas/cloud run. But even those have their own set of challenges/costs. Managing Kubernetes can get complicated and expensive quickly, especially if you’re not already using it for your app. On the other hand, serverless options like Lambda or Cloud Run introduce latency issues (cold starts) and often don’t provide the flexibility you need for long-running sessions or custom configurations.

          Then, beyond the infra, we'll probably need to build capabilities to not get stopped out by anti-bot measures like proxy mgmt, fingerprint rotation, captcha solving, etc.

          Pretty quickly, as you grow, a small-scale project can turn into a pretty big maintenance project. Building parsers/agents/scripts is hard enough, so we're hoping to make the infra side as easy as possible.

      • bleachpedro31 周前
        So this is the Vercel approach to web bots? Hopefully less predatory aha..
        • huss971 周前
          haha, I love this analogy! If we can do for deploying web automation to prod what Vercel did for deploying front-ends, I'd be a happy camper. With even friendlier pricing of course :P
      • peab2 天前
        I can relate to this exact experience and I think anybody who's tried to bring scraping to prod can as well!
        • huss972 天前
          haha love to hear that :) we want to make that experience trivial
      • meiraleal2 天前
        And why run in the cloud in place of my own computer, with my own IP that won't be flagged for being an AWS IP?
  • potamic2 天前
    Browser as a service I understand, but what is the "for AI agents" part?
    • huss972 天前
      ah, we could definitely do better in communicating that. Most of the work is ahead of us but we currently help ai devs in a few ways: - designing with sessions as the atomic unit -- we wanted them to be spun up and discarded in a serverless way w quick boot times. That way you would have these quick or long-running sessions that agents can just jump in and out of or as a building block for custom tools. We also expose debug urls so you can embed viewable sessions into you app in a Devin-esque UI. - In the Open-source API, we expose some features that allow you to turn webpages into more LLM-friendly formats for consumption like: markdown, readability, screenshots, and pdfs.

      It does just so happen that it ends up being useful for non AI apps as well

  • amelius2 天前
    Is there any AI out there that can detect and fill in WiFi login pages typically found on hotel and company guest networks?
    • ohthatsnas2 天前
      Haven't tried to build one myself, but that would be a cool project.

      If it's a login page that gets redirected to when you try to access a page on your browser, then theoretically you should be able to do that with the open source repo and custom AI logic.

      Having to constantly fill out those login pages (especially for networks that expire) is such a pain so would love to use this myself lol

      • amelius1 天前
        Well, sometimes I want to start a WiFi connection without opening a webpage at all.

        So an AI that can fill in the WiFi login page should be able to do it without opening a browser.

  • Oras1 周前
    Looking interesting, will definitely give it a go.

    Btw, there is inconsistency between pricing page and pricing on docs.

    Pricing page for developers is $59 Pricing in docs for developers is $99

    • huss971 周前
      awesome - let us know how it goes!

      great catch on pricing mismatch, just fixed, thank you :)

  • benzguo2 天前
    beautiful docs + api ref! what are you using? (cool that you're doing open-source browserbase also, excited to check this out)
  • meiraleal2 天前
    Why not a browser extension?
    • ohthatsnas2 天前
      A browser extension would have to run on individual/personal browser; we're focused on providing infrastructure to run hundreds of browsers that you can connect to with code -- whether for automation or information retrieval.

      Curious, what made you think browser extension first? :)

      • meiraleal2 天前
        > Curious, what made you think browser extension first? :)

        It would be cheaper (free?) and easier to maintain, one could even use the chatgpt.com or claude.ai web app as API.

  • doritopope1 周前
    will definitely check this out. i saw the pricing model on the site, what's the motivation around being open-source here if you're providing the infra free of charge?
    • ohthatsnas1 周前
      Yeah, good question! The reason we went open-source is really about transparency and flexibility. We want people to trust what they’re using and have the option to self-host if that’s what makes the most sense for them. Open-sourcing the browser API also lets us build a better product with input and contributions from the community—it’s a win-win.

      As for the infra, it’s not totally free—our managed service is there for anyone who doesn’t want the hassle of hosting and scaling everything themselves (although it does have a generous free plan). Going open-source just gives people the choice: run it yourself if you want full control, or use our managed option for convenience and scale. It’s all about making browser automation more accessible without forcing people into one path.

  • tndibona2 天前
    Can this defeat perimeterX used by Zillow?
    • ohthatsnas2 天前
      Hey! So we don't explicitly support perimeterX, but some of our users have been able to consistently bypass perimeterX using custom proxies (and some of our own as well).

      We'll probably take a deeper look at this in the next few weeks and expand on what we work with vs what we don't.

  • puppycodes2 天前
    I cant find any information on models you support?
    • ohthatsnas2 天前
      You can use any model on top of us! We only provide browser infrastructure, so multiple warm browsers that you can connect to and drive using puppeteer, playwright, selenium, etc.

      So you would just need to add some wrapper code and call those actions using a model of your choice.

      We're working on more examples and guides that show how you can do this, so keep an eye out on our releases or hop in the discord and you should see some specific examples very soon!