web-applets VS wcgw

That's specifically what I'm working on at [Unternet](https://unternet.co/), based on observing the same issue while working at Adept. It seems absurd that in the future we'll have developers building full GUI apps that users never see, because they're being used by GPU-crunching vision models, which then in turn create their own interfaces for end-users.

Instead we need apps that have a human interface for users, and a machine interface for models. I've been building [web applets](https://github.com/unternet-co/web-applets/) as an lightweight protocol on top of the web to achieve this. It's in early stages, but I'm inviting the first projects to start building with it & accepting contributions.

For those interested, I've been working on something related to this, Web Applets – which is a spec for creating AI-enabled components that can receive actions & respond with state:

https://github.com/unternet-co/web-applets/

Awesome! I essentially started with the same premise when coding "wcgw" [1]. Give a single shell tool to chatgpt (later claude).

Chronology that followed:

1. Some processes take long time: add status checking.

2. Need to kill long running process or interact with tools add option to send control characters; BashInteraction tool.

3. File editing using sed and echo is not reliable, add FileEdit tool.

4. Large output; add truncation based on tokens.

5. But wait I need command output to get truncated at the beginning but file reading `cat $file` to truncate at the end. Add special ReadFile tool.

6. File writing using 'echo "content" >file' needs unncessary quotes escaping leading to degraded quality, add special WriteFile tool.

7. Reading one file at a time is slow, change ReadFile to ReadFiles tool.

8. Directly writing files is not as good as first planning things. Prevent writing using architect mode.

And so on.

[1] https://github.com/rusiaaman/wcgw

Good work.

I wonder if there's really a need for separate write to terminal and read output functions? I was hoping that write command itself would execute and return the output of the command, saving back and forth latency.

> and it's not always clear when the job is done

I've authored a similar mcp [1] (but without terminal ui)

The way I solved it is by setting a special PS1 prompt. So as soon as I get that prompt I know the task is done. I wonder if a similar thing can be done in your mcp?

[1] https://github.com/rusiaaman/wcgw

You can basically get the same experience as aider with an MCP server like https://github.com/rusiaaman/wcgw. It's not perfect - sometimes has trouble with exact syntax of find/replace. But it's free to use up to your regular Claude subscription usage limit. I actually use it more than Cursor, because it's easier to flip back and forth between architecting/editing.

For building mcp server? The official docs do a great job

https://modelcontextprotocol.io/introduction

My own mcp server could be an inspiration on Mac. It's based on pexpect to enable repl session and has some tricks to prevent bad commands.

https://github.com/rusiaaman/wcgw

However, I recommend creating one with your own customised prompts and tools for maximum benefit.

Personally I'm using the Filesystem server along with the mcp server called wcgw[0] that provides a FileEdit action. I use MacWhisper[1] to dictate. I use `tree` to give Claude a map of the directory I'm interested in editing. I usually opt to run terminal commands myself for better control though wcgw does that too. I keep the repo open in a Cursor/Windsurf window for other edits I need.

But other than that I basically just tell the model what I want to do and it does it, lol. I like the Claude Desktop App interface better than trying to do things in Cursor/Windsurf directly, I like the ability to organize prompts/conversations in terms of projects and easily include context. I also honestly just have a funny feeling that the Claude web app often performs better than the API responses I get from the IDEs.

[0] https://github.com/rusiaaman/wcgw

[1] https://goodsnooze.gumroad.com/l/macwhisper

It's great! I quickly reorganised my custom gpt repo to build a shell agent using MCP.

https://github.com/rusiaaman/wcgw/blob/main/src/wcgw/client/...

Already getting value out of it.