Probably the same reason as oh-my-zsh, you don't need 90% of it. Further compounding the problem in an agent harness is that you are polluting the context window by throwing the kitchen sink at it.
- it allows different models within one session via roles (I only have API, so pay per token)
- it's much more likely (ime) to use the LSP over grep for determining how code fits together
But I agree a 20k+ starting context is way overkill.
I find it's very hard to get information on harnesses people are using. I have to stay model agnostic so I avoid claude, codex, cursor, etc. I've used and tried opencode, which worked well, but obviously lacks the above features.
Does anyone have a resource for following what people are actually being productive with? With so much vibe going on it's hard to separate the wheat from the chaff.
Can you explain your opinion? I'm curious but such vague comments won't convince me.
Probably the same reason as oh-my-zsh, you don't need 90% of it. Further compounding the problem in an agent harness is that you are polluting the context window by throwing the kitchen sink at it.
I've been experimenting with omp because:
- it allows different models within one session via roles (I only have API, so pay per token)
- it's much more likely (ime) to use the LSP over grep for determining how code fits together
But I agree a 20k+ starting context is way overkill.
I find it's very hard to get information on harnesses people are using. I have to stay model agnostic so I avoid claude, codex, cursor, etc. I've used and tried opencode, which worked well, but obviously lacks the above features.
Does anyone have a resource for following what people are actually being productive with? With so much vibe going on it's hard to separate the wheat from the chaff.
this summarizes the average OMP user and dev
https://x.com/greg_horvay/status/2100764473392820433?s=20
What a crazy thread lol. I really can't tell who is serious and who isn't there.
Again, this is vagueposting, what do you have against snapcompaction? It seems to be a nifty way to save token costs. At least it's an interesting innovation. https://x.com/_can1357/article/2064802476742574459?lang=en
what do you use and why do you prefer it over omp
Just pi. `pi install` the packages you actually need or ask LLM to write a package for you. Keeping the harness minimal is the point of pi.
you are a joke if you think omp is a joke.