Hey HN, we're Glenn and Julian, and we're building stagewise (https://stagewise.io), a frontend coding agent that inside your app’s dev mode and that makes changes in your local codebase.

We’re compatible with any framework and any component library. Think of it like a v0 of Lovable that works locally and with any existing codebase.

You can spawn the agent into locally running web apps in dev mode with `npx stagewise` from the project root. The agent lets you then click on HTML Elements in your app, enter prompts like 'increase the height here' and will implement the changes in your source code.

Before stagewise, we were building a vertical SaaS for logistics from scratch and loved using prototyping tools like v0 or lovable to get to the first version. But when switching from v0/ lovable to Cursor for local development, we felt like the frontend magic was gone. So, we decided to build stagewise to bring that same magic to local development.

The first version of stagewise just forwarded a prompt with browser context to existing IDEs and agents (Cursor, Cline, ..) and went viral on X after we open sourced it. However, the APIs of existing coding agents were very limiting, so we figured that building our own agent would unlock the full potential of stagewise.

Since our last Show HN (https://news.ycombinator.com/item?id=44798553), we launched a few very important features and changes: You now have a proprietary chat history with the agent, an undo button to revert changes, and we increased the amount of free credits AND reduced the pricing by 50%. We made a video about all these changes, showing you how stagewise works: https://x.com/goetzejulian/status/1959835222712955140/video/....

So far, we've seen great adoption from non-technical users who wanted to continue building their lovable prototype locally. We personally use the agent almost daily to make changes to our landing page and to build the UI of new features on our console (https://console.stagewise.io).

If you have an app running in dev mode, simply `cd` into the app directory and run `npx stagewise` - the agent should appear, ready to play with.

We're very excited to hear your feedback!

Pet peeve because everyone seems to be doing this:

The video demo shows the operator asking for "same height", and then the agent sets a hardcoded 298px height instead of using any of the many reliable/solid ways to do it with CSS.

I'm sure there are better examples you could prompt to make that video convincing, though I appreciate the honesty showing what to expect.

Unrelated to the actual product (which looks nice), I'm always curious when I see these landing pages with logos from massive companies on them. I'd bet a beer that you didn't go through Oracle's processes for using their logo, for example. Are you just YOLOing it and hoping they don't come after you for unauthorised use?

I really liked the look of the product, but since the founder replied multiple times to questions / comments some thing along the lines of “we have not really spent time on…” comes across not very well thought out!

However I am personally looking for a product exactly like this! I really want LLMs to make beautiful UI for me.

Weird how you can’t sign up except via the CLI. And pricing isnt posted publicly and usage isn’t documented. The docs leave something to be desired as well. Would be nice to show more info for running this with a backend process as well

Cool product! I have a question outside of this topic: how did you manage your open-source processes from day one, and how did you encourage people to contribute to the project?

I can't find info on your GitHub pages how dataflow works in this tool.

You can show an example of what is looking for and what is actually being sent to LLM

this should be sandboxed by default, running agents directly on the host is a horrible idea.