I really like Pi, especially for when you're running a local model and your context is particularly limited. But even when running a big model, I think building up your environment to be exactly what you want can be really powerful.
When I was first getting started and didn't realize that ollama defaults to incredibly tiny amounts of context, Pi was the only harness that actually worked because the rest of them used up all of the context and then some with the system prompt. However, these days I've figure out llama.cpp and proper context sizes.
OpenChamber has been the real game-changer that caused me to switch back to OpenCode, though. I love being able to check in on it from my phone, a browser, etc. instead of having to be at my computer to get anything done.
When I was first getting started and didn't realize that ollama defaults to incredibly tiny amounts of context, Pi was the only harness that actually worked because the rest of them used up all of the context and then some with the system prompt. However, these days I've figure out llama.cpp and proper context sizes.
OpenChamber has been the real game-changer that caused me to switch back to OpenCode, though. I love being able to check in on it from my phone, a browser, etc. instead of having to be at my computer to get anything done.