Show HN: Open source alternative to Perplexity Comet

(browseros.com)

166 points | by felarof 9 hours ago

18 comments

  • azinman2 2 hours ago
    The demo buying toothpaste shows the difficulty of these tasks. Toothpaste itself was very underspecified, and it essentially randomly chose from a huge list. Some tasks may have past actions that could help guide, others won't have any to inform. Failure cases abound -- maybe the toothpaste you previously bought is no longer available. Then what? Ultimately how much time did this particular example save since you need to double check the result anyway? This is what doomed Alexa for the purchasing experience that Amazon assumed it would enable in the first place.

    I think it'd be better to show more non-trivial examples where the time savings is clear, and the failure cases are minimized... or even better how it's going to recover from those failure cases. Do I get a bespoke UI for the specific problem? Talk to it via chat?

    This whole world is non-trivial. Good luck!

    • felarof 1 hour ago
      Great points! For sure, the whole agentic browsers space is still super early.

      We are also just getting started and trying to narrow down on a high-value niche use-case.

      There are few repetitive, boring use-cases where time saving could be meaningful -- one example: Walmart 3rd-party sellers routinely (multiple times a day) keep checking prices of the competitor products to price their products appropriately. This could be easily automated with current agentic browsers.

      • byteknight 1 hour ago
        But in reality, would much more consistently be automated by a single playwright script.
        • felarof 1 hour ago
          True, there are plenty of libs already available to do such an automation if you are (or can hire a) dev.

          But for non-technical folks, agentic browsers seems like a good UX to build such and many more automations.

  • mdaniel 3 hours ago
    > --- How we built? We patch Chromium's C++ source code with our changes, so we have the same security as Google Chrome. We also have an auto-updater for security patches and regular updates.

    So you rebuild your browser on every Chromium release? Because that's the risk: often changes go into Chromium with very innocent looking commit messages than are released from embargo 90 days later in their CVE reference

    • felarof 3 hours ago
      Good question, so far we have been building on top of chromium release that Google Chrome is based on.
  • 5xpB7n8tdbtoP 20 minutes ago
    The windows .zip shared on your github release page gets flagged as a Trojan by windows defender. Why is it a zip in the first place?
    • felarof 15 minutes ago
      It is just a warning. We working on getting Microsft Windows signing set up.
  • thegeek108 15 minutes ago
    The name is confused. I think it is a web-based OS in the first place.
    • felarof 8 minutes ago
      Hmm, what do you mean? Could you elaborate? Thanks!
  • layer8 8 hours ago
    I would prefer this as a browser extension, not as its own browser application.
    • felarof 7 hours ago
      We would've preferred to build this as browser extension too.

      But we strongly believe that for building a good agent co-pilot we need bunch of changes at Chromium C++ code level. For example, chromium has a accessibility tree for every website, but doesn't expose it as an API to chrome extension. Having access to accessibility tree would greatly improve agent execution.

      We are also building bunch of changes in C++ for agents to interact with websites -- functions like click, elements with indexes. You can inject JS for doing this but it is 20-40X slower.

      • layer8 4 hours ago
        Would this be possible for Firefox?
        • felarof 3 hours ago
          IIRC, Firefox's web extension API does not provide access to accessibility tree as well.
          • dotancohen 1 hour ago
            I'm not GP, but I agree that if your goal is to empower the end user and protect him from corporate overlords, then Firefox is a more logical choice to fork from.
            • axus 37 minutes ago
              I wonder if someone on the Chromium team will upstream all these BrowserOS changes, or "Not Invented Here" and re-implement it all for Gemini / Google Assistant.

              Can't imagine Firefox acquiring a Firefox fork!

      • esafak 6 hours ago
        Could you upstream that change in order to make it an extension in the future? I think people would not value it any less.
        • felarof 6 hours ago
          We don't mind upstreaming. But I don't think Google Chrome/Chromium wants to expose it as an API chrome extensions, if not they would've done this long time ago.

          From Google's perspective, extension are meant to be lightweight applications, with restricted access.

          • jazzyjackson 3 hours ago
            I'm not really interested in AI agents for my webbrowser, but it would be pretty cool to see a fork of chromium available that, aside from being de-googled, relaxes all the "restricted access" to make it more fun to modify and customize the way you guys are. Just a thought, may be more of a market for the framework more than the product :)

            See Sciter. A very cool, super lightweight alternative to Electron, but unfortunately it seems like a single developer project and I could never get any of the examples to run.

            https://sciter.com/

            • felarof 3 hours ago
              Yes, we want to do this too! We'll expose much more richer APIs.

              What use-cases do you have in mind? like scraping?

      • arjunchint 3 hours ago
        I mean you could build the agent with a first principles understanding of the DOM instead of just hacking together with the accessibility tree
    • arjunchint 3 hours ago
      We had this exact thought as well, you don't need a whole browser to implement the agentic capabilities, you can implement the whole thing with the limited permissions of a browser extension.

      There are plenty of zero day exploit patches that Google immediately rolls out and not to mention all the other features that Google doesn't push to Chromium. I wouldn't trust a random open source project for my day-to-day browser.

      Check out rtrvr.ai for a working implementation, we are an AI Web Agent browser extension that meets you where your workflows already are.

      • felarof 1 hour ago
        Brave Browser (70M+ users) has validated that a chromium fork can be viable path. And it can in fact provide better privacy and security.

        Chrome extensions is not a bad idea too. Just saying that owning the underlying source code has some strong advantages in the long term (being able to use C++ for a11y tree, DOM handling, etc -- which will be 20-40X faster than injecting JS using chrome extension).

  • rpastuszak 8 hours ago
    Congrats!

    How are you planning to make the project sustainable (from a financial, and dev work/maintenance pov)?

    • felarof 7 hours ago
      Thank you!

      plan is to sell licenses for Enterprise-version of browser, same as other open-source projects.

    • patrickaljord 8 hours ago
      my guess is it's just an electron app or chromium wrapper with an ollama wrapper to talk to it (there are plenty of free open source libs to control browsers).
      • felarof 7 hours ago
        We are a chromium "wrapper"

        But we are much more performant than other libs (like playwright) which are written in JS, as we implement bunch of changes at chromium source code level -- for example, we are currently implementing a way to build enriched DOMtree required for agent interactions (click, input text, find element) directly at C++ level.

        We also plan to expose those APIs to devs.

      • janalsncm 8 hours ago
        “Just” is a four-letter word :)

        When someone in their infinite wisdom decides to refactor an api and deprecate the old one, it creates work for everyone downstream.

        Maybe as an industry we can agree to do this every so often to keep the LLMs at bay for as long as possible. We can take a page out of the book of the maintainers of moviepy for shuffling their apis around, it definitely keeps everyone on their toes.

      • moscoe 7 hours ago
        You don’t have to guess, it’s open source
      • lotyrin 2 hours ago
        No wireless. Less space than a Nomad.
  • darkmuck 2 hours ago
    This is similar to the chrome extension nanobrowser. https://github.com/nanobrowser/nanobrowser
  • eGQjxkKF6fif 8 hours ago
    Whats the roadmap looking like for Linux?

    I don't have Mac or Windows.

    • felarof 7 hours ago
      this is on our radar, we plan to have it ready by early next week!

      still a team of 2 people, so bunch things on our plate.

  • bkyan 1 hour ago
    Is there a way to hook BrowserOS up as a sub-agent for an orchestration agent/system?
    • felarof 1 hour ago
      Yes! We want to do this.

      We were thinking of implement MCP protocol into the browser, so the browser can be an MCP server (that exposes bunch of tools -- navigation, click, extract) and you can connect that to your agent, would that work?

      What is your use-case? Happy to chat on discord! https://discord.gg/YKwjt5vuKr

      • bkyan 55 minutes ago
        Yes, that works for me! My primary use case is automated testing of updates to websites that I maintain.
      • bkyan 46 minutes ago
        Thanks for the discord invite! My username is Mindcast on discord.
        • felarof 34 minutes ago
          thanks for joining! DMed you.
  • o_____________o 3 hours ago
    Would love to see this show up on homebrew!
    • felarof 3 hours ago
      Oooh, that's a nice idea! We'll look into doing that!
      • mh- 2 hours ago
        Making a homebrew recipe is super easy, and you can definitely find an example to draw from that's "shaped" like your app. Highly recommend.
  • zebomon 5 hours ago
    This is very exciting given the rumor that OpenAI will be launching a (presumably not open source) browser of their own this summer. I've joined your Discord, so will try it soon and report back there. Congrats on launching!
    • felarof 5 hours ago
      Thank you!

      Browser wars have begun.

      > that OpenAI will be launching a (presumably not open source) browser of their own this summer.

      For sure, won't be open-source. I bet in some parallel world, openAI would be non-profit and actually open-source AI :)

  • DANmode 2 hours ago
    Is BrowserOS-OS on the roadmap?

    (Will you ever make a better FydeOS, or if you're laser-focused, perhaps be open to sharing some with them, so they could?)

    • felarof 1 hour ago
      Yes! We are excited to build BrowserOS-OS! I think with agents the whole UX can be re-imagined.

      I'll check out FydeOS!

  • daureg 6 hours ago
    > our agent runs locally in your browser (not on their server)

    That's definitely a nice feature. Did you measure the impact on laptop battery life in a typical scenario (assuming there is such a scenario at this early stage)

    • felarof 6 hours ago
      The agent running by itself shouldn't impact battery life, it is similar to a lightweight chrome extension and if you think about it, it's an agent browsing the web like human would :)

      If you run LLMs locally (using Ollama) and use that in our browser, that would impact battery life for sure.

  • arjunchint 3 hours ago
    Do you have any benchmarks to share like Halluminate's Web Bench?
    • felarof 2 hours ago
      We working on it! Should have pretty soon!
  • closetkantian 5 hours ago
    This looks like a great project.

    What are the system requirements? And shouldn't they be listed on your website?

    • felarof 5 hours ago
      we support Mac (apple silicon and intel) and Windows.

      hardware requirements are minimal, same as Google Chrome, if you BYOK API keys for agents and are not running LLMs locally.

  • ivape 3 hours ago
    What is the default BrowserOS model? Is it local, and if so, what inferencing server are you using?
    • felarof 3 hours ago
      The default model is Gemini.

      You can bring your own API keys and change the default to any model you local.

      Or better run model locally using Ollama and use that!

      • ivape 3 hours ago
        The default is a remote Gemini call?
        • felarof 1 hour ago
          Yes, right now using Gemini API on our liteLLM server (we can't expose API key on client side).

          We are working on smaller, fine-tuned model too, which will be the default soon! It should be much faster and precise at navigation tasks.

  • paul7986 4 hours ago
    So would this or any AI browser go out and fetch a list of the best deals for my trip to Iceland? After Show me all the options it has found for flights, hotels, car rentals and show cheapest/best prices with all details (fly out of and into with times) to even allow me to pay for each item on same page I asked it to do so? As well it could group the overall best deal with details and then i can just click to pay instantly and or make some edits.
    • flymasterv 29 minutes ago
      Orbitz.com has done this for 20 years.
    • dotancohen 1 hour ago
      It seems that the next evolution of SEO will be too skip the SE and simply O for the LLMs.
    • felarof 3 hours ago
      We just started cooking, very soon you should be able to do this!