IME Claude has been a bit inferior. But, yeah, the marketing is just great.

So what? Surely they're just guessing and actually have no idea.

I absolutely like this. Pi becomes sluggish after installing a couple of extensions. I myself was trying to port Pi to Rust but it was consuming too much tokens.

Is there any API like Pi so that I can create extensions.

It absolutely doesn't. It must be the extensions you're using.

I've found is that nearly every extension on the official pi.dev/packages is vibe coded trash, like for example the most popular subagents extension.

Instead of just giving you a basic subagent, it's a whole kitchen sink of recursion, teams, chains, confusingly named agents like "oracle" etc. Basically feels like someone kept prompting "what else could we add here?".

They're all like that. It's no wonder these slow down pi.

What I've done is just have the agent write my own.

Get a local copy of e.g. that kitchen sink subagents extension. Have the agent list all the features, then I give back a much smaller list of the features I want and say "write me a new extension with just these new features" and every time it one shots it (using GPT 5.3 usually), then 20-30 minutes later I have a working, lightweight extension tuned to my exact workflow.

I've done this for I guess about 8 extensions now (subagents, a lightweight typescript LSP, web search, background processes, Claude style hooks, plan mode are the main ones) and it's very fast and snappy.

Still they are maintained by those developers. I cannot spend my time developing extensions. I'd rather do that in Rust.

Then pi is probably not for you, as doing this is pretty much the whole selling point. You could try oh-my-pi or OpenCode instead.

Working on a native non JS Http client similar to Insomnia.

Bun is basically a wrapper over JSCore. I don't think it's that big of a feat. Furthermore they are heavily invested in vendor specific APIs which I think is not good.

Using that logic, Node.js is just a wrapper over V8.

Indeed it is

Great!

It's GPT 5.5 and it still can't do exactly the same thing I want. So, I think companies should call AI a lost cause.

Do we have any performance benchmark with token length? Now that the context size is 1 M. I would want to know if I can exhaust all of that or should I clear earlier?

There's also time limits, challenges before opening apps to create fiction, quiet hours so u don't scroll at night, usage tracking, opening with intention so it asks what u wanna do in the app, and then let's u for example only stay in DM's tab.

All I want is auto complete for the commands on Windows. And none provides

Take a look at clink[1]. Or use PowerShell.

[1]: https://chrisant996.github.io/clink/

I do use powershell but it doesn’t provide auto complete for commands. I repeat I don’t want history. I want commands or args suggestions. Just like zsh auto complete