Main take away is that OMP (oh my pi) is very extendable.
Since DeepSeek V4 doesn’t have vision so he got OMP to use GPT 5.6 Luna using the Codex sub.
DeepSeek also doesn’t support web search so he wired up OMP to call agy (Antigravity CLI) directly since using the Antigravity sub with Pi or OMP will get you banned.
This is an incredibly powerful paradigm since you can mix and match models for their best capabilities.
Can you actually have an agent call the Antigravity CLI by the TOS? Feels like the type of thing that would get your account flagged by doing it programmatically.
It wasn't long ago when calling Claude -p would trigger usage billing. I don't know if they backtracked that but even apps like T3 Code were warned that using Claude like that was not going to use the Claude sub.
Main take away is that OMP (oh my pi) is very extendable.
Since DeepSeek V4 doesn’t have vision so he got OMP to use GPT 5.6 Luna using the Codex sub.
DeepSeek also doesn’t support web search so he wired up OMP to call agy (Antigravity CLI) directly since using the Antigravity sub with Pi or OMP will get you banned.
This is an incredibly powerful paradigm since you can mix and match models for their best capabilities.
Can you actually have an agent call the Antigravity CLI by the TOS? Feels like the type of thing that would get your account flagged by doing it programmatically.
It wasn't long ago when calling Claude -p would trigger usage billing. I don't know if they backtracked that but even apps like T3 Code were warned that using Claude like that was not going to use the Claude sub.
How can they know when used with agy -p?
Sounds very hacked together
So actually using the extensibility and configurability of pi/omp means it’s “hacked together”?
No, it's mor the fact that you're doing these iffy cli calls that I have a problem with
Literally everything about AI coding is hacked together. Top to bottom, from every player.