Hacker Newsnew | past | comments | ask | show | jobs | submit | messh's commentslogin

how does it differ from playwright-cli?

At its core, libretto generates, validates, and helps with debugging RPA scripts. As far as I understand tools like playwright CLI are more focused on letting your agent use playwright to perform one-off automations.

The implementation is also pretty different:

- libretto gives your agent a single exec tool (instead of different tools for each action) so it can write arbitrary playwright/javascript and is more context efficient

- Also we gave libretto instructions on bot detection avoidance so that it will prefer using network requests for automation (something that other tools don’t support), but will fall back to playwright if it identifies network requests as too risky


playwright-cli is very simple and meant for humans - it basically generates a first draft of a script, and was originally meant for writing e2e tests. You need to do a lot of post-processing on it to get it to be a reliable automation.

libretto gives a similar ability for agents for building scripts but:

- agents automatically run, debug, and test the integrations they write - they have a much better understanding of the semantics of the actions you take (vs. playwright auto-assuming based on where you clicked) - they can parse network requests and use those to make direct API calls instead

there's fundamentally a mismatch where playwright-cli is for building e2e test scripts for your own app but libretto is for building robust web automations


It doesn't solve recording and uploading later... say a movie. So how does it even make sense?

Games are time-sensitive events. Most people who care don't want to watch the game once it's finished, they want to watch it live.

you can spin similar instances very cheaply and billed only for the time openclaw actually runs in https://shellbox.dev ($0.02 for 2vcpu, 4gb ram, 50gb hdd, real linux with headless chrome etc)

https://sprites.dev as well (it’s a fly.io product). They look suspiciously identical…

Checkout shellbox.dev, you can do pretty much the same, automating it all bia ssh

How is this different than say bubblewrap and others?


https://jai.scs.stanford.edu/comparison.html#jai-vs-bubblewr...

> bubblewrap is more flexible and works without root. jai is more opinionated and requires far less ceremony for the common case. The 15-flag bwrap invocation that turns into a wrapper script is exactly the friction jai is designed to remove.

Plus some other comparisons, check the page


bubblewrap is in many modern distros standard packages.

With all the supply chain issues these days onboarding new tools carries extra risks. So, question is if it's worth it.


Can be significantly cheaper on a vm that wakes up only when yhe agebt works, see for e.g. https://shellbox.dev


but if you move to gpt-5.4 ?


It's down for me


so.... is RTO optional


idk, seems being single rocks :) I have not time for myself at all


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: