Regarding next steps, we're currently working on React integration, with Python and JavaScript server-side web frameworks coming next. If you're interested, here's our survey/waiting list: https://forms.gle/8MeXwGjpBFDeGNQw9
I only have one question and it's not a very important one; the name.
Why is it "tidewave" and not "tidalwave"? That just sounds wrong. (Told you it wasn't important :D )
EDIT: I think I might have answered my own question, there's another AI mortgage payment tool already called Tidalwave. I guess this saves confusion.
Our announcement post goes more into detail and explains why moving the agent to the browser means you (the developer) can spend more time out of the loop: https://tidewave.ai/blog/tidewave-web-phoenix-rails
> "This Rails MCP Server implements the MCP specification to give AI models access to Rails projects for code analysis, exploration, and assistance."
And again I don't get the value. I can see some slight benefits to having a tight browser integration but I don't think that's worth leaving the IDE / CLI tools and the workflows they bring. You can also use Playwright MCP or just screenshot easily for more context. Claude Code can now run your server in the background and view logs as well. In a perfect world where LLM's can one shot whole features, maybe. But I can't let Claude Code go 10 minutes without it introducing a bad pattern and having to stop it. Reducing that visibility even further with this does not seem like a good combo.
I'm not wanting to tear down others projects either, just giving my perspective. I should try it to see how it does in the wild but the Copilot license or Anthropic API key requirement also deters me as well as having to have a project specific dependency.
First, Playwright MCP is really not enough. For example, imagine you are building a project management software and you are working on a feature for transferring tasks between projects. Testing this feature requires at least a user who is admin and at least two projects. When it is time for Playwright to test this feature, you need to automate the account creation, then it has to set up two projects, add the task, etc, and it often gets stuck.
When you are using Tidewave, you naturally do this setup as part of your development, which Tidewave has direct access to during tests. So it just interacts with the same page. Furthermore, if you see any bugs or places you could improve, you can't really tell Playwright or regular coding agent to fix them, you have to translate what you want. With Tidewave you just point and click and it works across browsers. I talk more about this in the announcement post: https://tidewave.ai/blog/tidewave-web-phoenix-rails
Other than that, I am really curious about the handoff between Tidewave and the editor that you mentioned. At some point, you will need the editor indeed, but how to best do this transaction? Should you be able to review and do tiny tweaks within Tidewave first? Regardless, moving the agent to the browser for web applications bring enough benefits to justify going one lever higher. :)
You may want to point it to an Agents.md with usage rules synced: https://hexdocs.pm/usage_rules/readme.html
I ran this yesterday. Since it's running inside your app and has access to everything your app does, here's what it did for me:
I have an app that processes images and displays certain info on them. The images are processed asynchronously.
I needed a pubsub when info was inserted into the DB to be sent out, and info on the page to appear immediately.
Since Tidewave is running inside the app, it did the following:
- opened the info page
- triggered dummy data insert into the DB
Edit: I mean it inserted data using the exposed module functions that would trigger the pubsub [1], it did not add data to DB directly
- monitored both the app logs and the page to see what's happening
- made several iterations adding pubsub, subscribing to it, and fixing page display
I didn't need to make screenshots because Tidewave was looking at the page already.
I didn't need to paste screenshots anywhere and rely on that model's OCR to figure out what's going on.
I didn't have to copy-paste logs.
and so on
The login process didn't work well, but it's due to my browser having a seperate container for Github.
I asked it to add a feature using Stimulus.js to my very simple gallery page written in Rails, when you hover over an image in the gallery, it should make an icon appear, and when clicking the icon, a modal should pop-up that allows the user to do cropping.
It picked up on my database models and it produced a very good result, however, it seemed to have issues verifying its solution, it particularly seemed to struggle with "on-hover".
The solution it produced was a lot better than what claude-code produced, and I liked the interface.
I also ended up hitting the limits on the Anthropic API, and it wasn't obvious to me what I should do in that case, but that's likely not the fault of Tidewave, and the Context Window Usage having a maximum of 200.0k also seemed very high, but that probably contributed to me hitting a limit.
We are going to introduce more visibility into the context limit and make it easier to summarize.
Regarding the on-hover, do you still have the snippets around that it tried? We instruct the model to dispatch events using the proper browser APIs and I wonder what it tried to do. I would love to hear more! You can ping me on Tidewave's Discord (https://discord.gg/5GhK7E54yA) or send me an email (see github.com/josevalim).
I've been loving Tidewave MCP since the day it launched and I wish I had that for all my work. I also fight the pain of driving web browsers through the playwright MCP every day, and while it's a huge help, it's also massively slow and kills my context window.
I want these problems solved. But I want them solved in a way that isn't unique to one stack, because I don't have the luxury of sticking to my preferred Elixir stack all the time. I also want them solved in a way that doesn't force me to take a huge backward step in my AI usage by bypassing my all-you-can-eat Max subscription.
The $10 subscription isn't that expensive, but then again, since this isn't a complete solution, it's going to be on top of other subs like Cursor/Max/Phoenix.new etc etc and it becomes death by a thousand cuts.
Maybe I just need to calm down a bit and not look at it as all-or-nothing.
Like, sure, switching to this full-time would be impossible. But maybe as a tool in my toolbox, where I pay $10 and use it once-in-a-while, when I have a tricky thing to do and it's worth me burning $10-20 on API tokens just to unblock me.
I'm just concerned that software development is fast becoming pay-to-play / pay-to-win, and that can quickly lead to chickenization, where prices are carefully titrated to shift most of the value to the tool providers.
We've seen this play out in infrastructure and tooling, and most orgs now "donate" a huge chunk of their profit margins to AWS.
The people did it to themselves.
Instead of investing time learning these things, people (like always) want to take a shortcut. Big co's are more than willing to take advantage of that laziness and will indefinitely into the future—whether diet pills, AI, or a brain chip that occasionally makes you drool but is 100x more accurate with directions than Google Maps.
The ability to have access to the context of the code, run tests and edit the code in place, are capabilities I could not even dream about when I started coding.
How Jose manages to see the potential of a technology (Erlang, LLM's) and produce something so elegant and useful is amazing. It has certainly changed my life.
yet this is Jose Valim we are talking about. creator of Elixir, Plug, contributor in Phoenix and Rails
Guy is a machine https://github.com/josevalim
I believe he will deliver, will check it time to time, interesting approach
Indeed. He is a big inspiration for Brazilian nerds.
To me this is an obvious direction for all coding agents to go in. Right now the cursor chrome browser MCP server doesn't work very well, but it's very obvious to me that this is the direction things need to go in.
I'm not sure why focusing on a framework would fundamentally make this any better than the generic approach to getting good context directly from the browser.
1. We annotate and understand your template language. So when you select an element, we not only know its tag and attributes, but we also know which template file rendered it. The more structured the template language is (JSX, HEEx, etc), the better job we can do, which means LLMs don't have to guess.
2. We also run code within the web framework. This means database access, built-in documentation using the exact versions in your project, access to language and framework reflection/introspection APIs, etc. So the agents have more, err, agency.
I hope this clarifies it a bit!
I can imagine having an in browser, framework level tool would know exactly which controller and which template generated this element and could target it more precisely while using less tool calls and less tokens. I haven't tested it yet but that is my expectation.
Is this because data is going through a tidewave server or something, or is it just a way to create a bit of a free trial vs "now you need to pay us"?
So far very good.
This would be such a game-changer. I am also convinced that monorepos will become the de facto standard, since it is way easier for LLMs to navigate / implement features across the whole stack.
Usually only one correct and idiomatic way to do things, and rails in particular really leans on convention over configuration.
Question: What happens to our data - i.e. the code and context sent to your service?
> I'd love to integrate with whatever model subscription is available but it seems using Max outside of Claude products is against their terms. I suggest reaching out to Anthropic and letting them know you would like to use your Max subscription with other coding agents.
<<<< Wave