[tomaytotomato]

I have been using Claude code for a while and have recently migrated to Pi

Migrating my skills/agents and config was fairly straightforward.

Pi's agent harness seems to be more responsive and quicker than CC (perhaps with the prompt caching and squashing it does behind the scenes)

Tempted to do a write-up on migration.

I am only using Pi with Github Copilot as I am scared I will get my Claude account banned if I use the Oauth with Pi.

pi.dev

[spudlyo]

Pi is the first, and and only agent I've ever seriously used, which I picked up after watching one of Marco Zechner's talks about it. His design approach and vision for pi resonated with me, and I've pretty much used it every day since. I, like Marco, am also a grumpy old person, so that might have had something to do with it. I have my own customizations for things like fuzzy autocompleting the name of Emacs buffers and symbols from my project's TAGS file, and a handful of skills. It's a pleasure to work with, and so far it's been my experience that if pi doesn't behave the way I want, it's pretty easy to modify to suit my needs.

OpenAI, as much as I dislike them, seems to be the only big AI lab that doesn't care what agent harness you use, so that's where my $100 a month goes.

[tasuki]

FYI the name is Mario Zechner[0]. I'm also grumpy and old and also use Pi for the same reasons as you. I also use an OpenAI subscription (the models aren't entirely bad), but am ready to jump ship to OpenCode Go or GLM Coding Plan any minute. And I've been watching the Claude Code shitshow with glee!

[0]: https://mariozechner.at/

[dsrtslnd23]

what is the current statement on Oauth Claude use with Pi. I remember there was some back and forth from Anthropic? I currently use my Claude sub with Pi.

[tomaytotomato]

No idea,

Anyone from Anthropic here who could answer this?