I built an AI "web harness" running on a sandboxed Chromium (using a custom side-loaded plugin that talks over websockets to a "driver") to basically do anything a normal user could do in a browser. It totally bypasses any and all bot measures and only gets the ones you yourself would get as well (and passes those successfully, e.g. Cloudflare checkbox or those annoying OCR puzzles).
Not sure if I should release it, but I'm sure more people are catching onto the power of agentic browsing.
There is no detection method that will prevent AI from accessing systems without also blocking humans. The only thing we can do at this point is throttling.
anyone can spin these kind of side projects and do easy talk, but the moment you actually try to use this on signed-in Linkedin or Amazon its going to fail
the only solution is to drive your regular browser with all your sessions/cookies via an extension
no it doesn't fail. Agents are very good at comparing traffic characteristics from a real browser and a headless/automation browser and getting it to behave in the same manner. It's a cat and mouse game for sites stopping unauthorized access but right now llm agents are ahead.
For testing proxies should be used to avoid IP ban issues but given enough time modern agents can figure out how to bypass most of the modern scraping/automation prevention mechanisms.
I have built and used a lot of different automations and web scraping implementations for my business and it's never got permanently stuck yet, some take a bit longer, some shorter, but all within a reasonable time with little external help they have succeeded in their tasks.
> the only solution is to drive your regular browser with all your sessions/cookies via an extension
This is exactly what I'm doing, but mocking/randomizing all the sessions/cookies/params (like resolution, OS, WebGL , etc.) in a separate Chromium binary. It's popular these days, but imo using your normal browser for agenting stuff is a very bad idea. These models do dumb stuff all the time.
It's sad, but this train has left the station a quarter of a century ago imo. Many people have since become billionaires scraping the web without anyone agreeing (Google, Yahoo, and now possibly Anthropic and OpenAI).
So of course I clicked yes and it dutifully convinced the site that it was not a bot.
Not sure if I should release it, but I'm sure more people are catching onto the power of agentic browsing.
Is that necessary? You could start Chromium with an open debug port and use Chrome Devtools Protocol to send commands.
Also it’s great(!) to see that we’re going from “but ethics” to “I got mine, who cares”.
Humans are interesting creatures.
the only solution is to drive your regular browser with all your sessions/cookies via an extension
For testing proxies should be used to avoid IP ban issues but given enough time modern agents can figure out how to bypass most of the modern scraping/automation prevention mechanisms.
I have built and used a lot of different automations and web scraping implementations for my business and it's never got permanently stuck yet, some take a bit longer, some shorter, but all within a reasonable time with little external help they have succeeded in their tasks.
This is exactly what I'm doing, but mocking/randomizing all the sessions/cookies/params (like resolution, OS, WebGL , etc.) in a separate Chromium binary. It's popular these days, but imo using your normal browser for agenting stuff is a very bad idea. These models do dumb stuff all the time.
Muse's utility has significantly dropped with the blockages.
To become truly useful again they will need to use residential proxies, but I can't see them use those due to the risks and reputational damage.