We're quite different than LaVague. LaVague passes in the entire HTML DOM to the LLM to help it generate XPaths and valid Selenium code. (https://github.com/lavague-ai/LaVague/blob/main/src/lavague/...)

Try this at your own risk.. any reasonable website would result in extraordinarily high input token costs

We spend quite a bit of our time building a layer between the HTML and the LLM call to distill important pieces of information down to actions the LLM can take.. better weighing cost vs output. We're still not at 100% coverage.

It is similar. hence the timing of the plug, probably :)