I tried cursor/claude code, but most of them just "code", they generate a lot of cells at once. But when i was working on data science project, i usually need to decide what code to write next based on previous cell result analysis, which i think runcell just did it!
The page is a showcase landing page example, not real product, the pricing are not for real product. It's just an open source and free CLI tool. Sorry for the confused information.
Sorry for the image, it just a placeholder image. I will just remove the placeholder image ot use some AI-generated images. It's not a landing page of real product, just a showcase of generated landing page
I just take some random screenshot, it just shows an example of landing page, not real product. sorry for the misleading design, will change the image soon
glad to see more discussion about local-first, but there havn't been a good business model for local first products, which might lead to the unsustainable of the tech ecosystem
It is still in proposal stage. Parts of them can be turned into element-based easily like card, badges. But others with returned value like buttons, checkbox will change the way of usage from streamlit offical components (like the return value of button is check status, but in element-based, it is an element).
I add some limit to the prompt and it is fixed temporally. I was thinking to transform the json struct to a flat struct with no keys before, but worrying about the structure it self can improve the accuracy of translation as context.