HackerTrans
TopNewTrendsCommentsPastAskShowJobs

theredsix

no profile record

Submissions

Show HN: Open-source browser for AI agents

github.com
155 points·by theredsix·4 miesiące temu·55 comments

Show HN: Deterministic browser control for AI agents (~90% on Mind2Web)

github.com
12 points·by theredsix·4 miesiące temu·7 comments

comments

theredsix
·2 miesiące temu·discuss
Genius I love it!
theredsix
·3 miesiące temu·discuss
Are you guys going to follow up with a paper showing EDEN results match or beat turboquant for needle in a haystack benchmarks?
theredsix
·3 miesiące temu·discuss
With AI you actually don't need to choose anymore. Well laid out abstractions actually make AI generate code faster and more accurately. Spending the time in camp 2 to design well and then using AI like camp 1 gives you the best of both worlds.
theredsix
·4 miesiące temu·discuss
Extrapolating the benchmarks, this would imply the best RYS 27B is capable of out performing the 397B MoE?
theredsix
·4 miesiące temu·discuss
super clever and awesome!
theredsix
·4 miesiące temu·discuss
The freeze sometimes does capture in between states. What I've seen the agent does in those cases is that it recognizes it's in between states and calls browser_wait(). Where the agent goes off the rails isn't a snapshot in the middle of a state transition, (it's smart enough to know to retry in that case), it's when the DOM changes after the agent believes the page has settled.

For async, lots of people smarter than me working on the smarter agent problem. Though there's a latency floor with inference due to prompt processing, and output generation. Without tools like ABP, the LLM is always aiming at a moving target.
theredsix
·4 miesiące temu·discuss
*bows
theredsix
·4 miesiące temu·discuss
It's a long shot but getting ABP to be a first party citizen alongside CDP would be my dream!
theredsix
·4 miesiące temu·discuss
Right now, it's evading all anti-botting detectors I've tested it on. I believe it's due to the fact it runs in headful mode and I've removed all detectable CDP signatures. Input events are also simulated at a system level (typing is at 200 WPM) so it's very hard for a page's javascript to detect it's not in a human operated chrome. A lot of detection on headless happens due to the webGPU capabilities being disabled since a modern computer is very unlikely to not support those. You could also wire up one of the Heretic models as a dedicated Captcha solver, I recommend Qwen 3.5 27b Heretic! https://huggingface.co/coder3101/Qwen3.5-27B-heretic
theredsix
·4 miesiące temu·discuss
Maintaining the fork isn't so bad, the core chromium changes are only a few hundred lines and I was able to extend already existing concept like debugger pausing and virtualtime emulation while riding off mojo IPC for cross thread communications.
theredsix
·4 miesiące temu·discuss
Exactly! This race condition is exactly the category of problems ABP will solve.
theredsix
·4 miesiące temu·discuss
Yes agreed, added to the roadmap!
theredsix
·4 miesiące temu·discuss
hmm, like adding an optional css selector for targeting?
theredsix
·4 miesiące temu·discuss
It runs in headful mode and all control signals are passed in as system events so it bypasses the problems browserbase identified.
theredsix
·4 miesiące temu·discuss
I've consolidated most of the changes in chrome/browser/abp and used shim's for the other modifications so rebase is light and handleable by Claude. I'd love to get this upstreamed. An intro to the chromium maintenance team would be greatly appreciated!
theredsix
·4 miesiące temu·discuss
/superpowers! that plugin is the GOAT
theredsix
·4 miesiące temu·discuss
those are factored into the wait heuristic only if there's a navigation event since clicks on an already loaded page won't trigger those. You can point Claude/codex at https://github.com/theredsix/agent-browser-protocol/tree/dev... and have it walk you through the wait heuristic step by step.
theredsix
·4 miesiące temu·discuss
Good question! ABP keeps a list of all same/parent/sibling network request and wait for them to complete within a timeout. If the timeout hits, it'll still freeze and screenshot back to the agent. There's a browser_wait() that the agent can call with increased timeouts to wait for network requests + DOM changes.
theredsix
·4 miesiące temu·discuss
Great insight! ABP exposes display resolution controls right now. I've noticed almost zero reCAPTCHAs during testing compared puppeteer stealth or other packages. Regarding the freezing mechanic, virtualtime is paused as well and the entire browser clock is captured so it would be very hard for a page's JavaScript to notice the time drift unless they were querying an external API clock.
theredsix
·4 miesiące temu·discuss
Updated the table!