Live data from Hacker News

Launch HN: Browser Use (YC W25) – open-source web agents

github.com

61–70 of 107 posts

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#61

I’m excited about the space and intend to keep an eye on you guys. I actually gave the opened source version of browser-use a try last week and ran into two problems: The first, it refused to correctly load the browser tab and would get stuck in a loop trying. I was able to manually override this behavior for the purpose of prototyping. The second, it hallucinated form input values. I provided it strict instructions…

Yeah - one version had that weird bug - we fixed it already (I think, super happy to tell me how to replicate if not).

Hmm really? Maybe you could use the sensitive data api to make it more deterministic? https://docs.browser-use.com/customize/sensitive-data

How would you imagine a perfect feedback loop?

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#62

Earlier quoted context omitted.

Yes, I was able to figure out a secure way to control the browser with AI Agents at rtrvr.ai without using debugger permissions/tools so it is most definitely possible. I meant by in production in the sense how you are advising your users to setup the local installation. Even if you launch browser use locally within a container but your restarting the user's Chrome in debug mode and controlling it with CDP from withi…

Injecting JS into the page or controlling it using extension APIs is not a secure way to control the browser.

Yeah, sorta feels like docker on a new instance is safer than connecting to actual browsers and injecting js code there… would love to skip cdp protocol though, it’s quite restrictive

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#63

Earlier quoted context omitted.

strong agree with this -- I don't understand outside of integration with Claude Desktop why to use MCP rather than a dedicated API endpoint.

I believe MCP helps here because it standardizes integrations, enhances user control via opt-in plugins, and improves security by avoiding direct endpoint calls. @gregpr07 wouldn't adoption of MCP open up Browser-use to more use cases?

It probably would yeah. I was very against it but this HN post sorta points me to “people want mcp”

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#64

Awesome job launching guys! We used Browser Use last week to order burgers from our smart glasses: https://x.com/caydengineer/status/1889835639316807980 One thing I'm hoping for is an increase in speed. Right now, the agent is slow for complex tasks, so we're still in an era where it might be better to codify popular tasks (eg: sending a WhatsApp message) instead of handling them with browser automation. Have yall lo…

That was such a cool demo man! We are working on speed, we are already 3-4x faster than operator with gpt4o

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#65
post #54

This looks fantastic — congrats on the launch. As an armchair observer, the agents + browser space feels like it’s waiting for someone to make the open source framework that everyone piles on to. Proxy rotation sounds like a solid way to monetize for businesses.

Yeah that’s precisely why we introduced the cloud version!

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#66

Earlier quoted context omitted.

imo if the website doesn't want us there the long term value is anyway not great (maybe exception is SERP apis or sth which live exlusively because google search api is brutally expensive). > extract data behind login walls We mean this more from a perspective of companies wanting it, but there is a login wall. For example (actual customer) - "I am a compliance company that has system from 2001 and interacting with i…

> imo if the website doesn't want us there the long term value is anyway not great Wat? You're saying if a website doesn't want your scraping their data then that data has low long-term value? Or are you saying something else because that makes no fucking sense.

Haha no, I am saying that if websites don’t want you there they will find a way to block you in the long run, so betting the product on extracting data from those websites is a bad business model (probably)

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#69

Have you inspected or thought through the security of your open source library? You are using debugger tools such as CDP, launching playwright without a sandbox, and guiding users to launch Chrome in debugger mode to connect to browser-use on their main browser. The debugging tools you use have active exploits that Google doesn't fix because they are supposed to be for debugging and not for production/general use. Th…

how would that work? Can you control the browser without debug mode? Especially in production the browsers are anyway running on single instance docker containers so the file system is not accesible... are there exploits that can do harm from a virtual machine?

Yes, you can control the browser without debug mode, and the common way to do it is ChromeDriver[1].

[1] https://developer.chrome.com/docs/chromedriver/get-started

Re: Launch HN: Browser Use (YC W25) – open-source web agents

#70
This looks very promising. Thank you for making it open source! At first glance, I couldn't find if you can run it using local models (ollama?). Is that at all possible?

Edit: for anyone else looking for this, it seems that you can: https://github.com/browser-use/browser-use/blob/70ae758a3bfa...

Post reply on HN