I thought, well my account is new, but I've seen 2hrs old account submit "Show HNs" with urls, easily.
And you get penalized for not posting URLs.
Finished working on a browser automation system via natural language and API calls.
This is how it's different than the likes Vercel browser, browser use, stage hand. e.t.c.
Handles identity / proxy management for you.
Handles server management with the aid of github.com/dashn9/serverless-flux enabling serverless browser computing. Spin as much AI browser process as possible. Extremely useful for startups and companies that wants to keep this internal.
Has less memory footprint and much faster (for obvious reasons - which is RUST!!!).
Works extremely well with faster, cheaper models. I'm always actively testing and developing with smaller models and will continue to do so, they are quite underestimated but tremendously capable.
High token efficiency. We don't dump full HTMLs in like browser use, also, I shifted away from screenshot, instead using a visual diff tree which works incredibly well
You just plugin your service account / AMI key (currently supports GCP, AWS) and in less than 30 seconds you are done with the setup. It downscales and upscales based on your demand. Once you are done. auto descales to the min servers you've set.
it's here: https://github.com/dashn9/rusty-browser
Other projects that enable for Rusty function are:
(Serverless management and deployment)[Flux: https://github.com/dashn9/serverless-flux ]
(Browser automation, BiDi and CDP)[Rustenium: https://github.com/dashn9/rustenium ]
(Browser automation, BiDi and CDP)[Rustenium Identity: https://github.com/dashn9/rustenium-identity ]
All contributions and advice and support are appreciated.
I'm working on a browser automation system via natural language and API calls.
Now you might ask? How is this different than the already existing ones like Vercel browser, browser use, stage hand. e.t.c?
Well none, NONE handles scaling and identity / proxy management for you, you'd have have to use the cloud service, and of course none written in RUST(the best PL ever).
This is excellently useful for companies that wants to keep this parts of their system internal for privacy / cost reason.
Rusty-Browser does.
You just plugin your service account / AMI key (currently supports GCP, AWS) and in less than 30 seconds you are done with the setup.
Now your limitation is how many servers your accounts can spawn. Noticed I said account, it's cloud agnostic and can run on multiple cloud accounts.
You need 2000 browsers running simultaneously for whatever purpose, web bots, trading bots, web scraping e.t.c. RustyBrowser has you. The beautiful part is it downscales and upscales based on your demand. Once you are done. auto descales to the min servers you've set.
Aside:
1. It also supports local usage 2. We don't dump raw html into the LLM, that's a waste, we leverage the Visual Tree of webpages to tell the LLM what to do, and to save on tokens we use a diff change on that tree so it knows exactly what changes made rather than redumping. 3. Also supports screenshots, however we prefer using it for the task evaluator rather than the instructor. 4. We are purposefully engineering it to work with cheaper, faster models like gpt-5.4-nano which works excellently well in filling out complex forms per our tests.
it's here: https://github.com/dashn9/rusty-browser
Other projects inspired for Rusty are:
(Serverless management and deployment)[Flux: https://github.com/dashn9/serverless-flux ] (Browser automation, BiDi and CDP)[Rustenium: https://github.com/dashn9/rustenium ]
It took me over three months to build the wonderful projects.
Please star the repo if you think it has some value, would encourage me to take it seriously and work more on it. All contributions and support are appreciated.
Thanks guys!!!
