Oh-my-pi is designed to be slim apparently but has a ton of useless features with little empirical justification. Pi is a good harness- probably the best, but OMP not so much.

One thing I hate about OMP more than anything else though: hash anchored edits. they don't work in practice; most models I've tried have spent more turns on repairing their broken edits than on the actual task.

▲

coffeeindex 2 days ago | parent | next [-]

From what I’ve read/heard, a lot of the power of Pi is its extensibility but it’s a hard sell for me to try it out just because I can extend it. How is it out of the box?

	▲	localroast 18 hours ago \| parent [-]
		You'd probably want at least some packages, like @henryqw/pi-auto-compact The system prompt is very slim, but Pi is obviously barebones. Biggest problem I find is there's no real configuring of when to compact, compaction is going to be manual. About half the packages available are various solutions to this problem. Out of the box it doesn't appear to support parallel tool calls, or at least the model I normally use (GLM 5.3 Flash) doesn't seem to make use of it. maybe just needs a simple note that parallel tool calls are available in the system prompt? I observe parallel tool calls with OMP. There's no MCP support either, but of course there's an extension for that as well. I'd be careful when using different providers or your OpenAI subscription. I'm not sure if Pi includes reasoning chains in the running conversation with each API call for every provider. I'm pretty sure reasoning is kept across the session with OpenRouter, at least. I always start Pi with '--no-skills'. I find it strange how they include skills as part of the base package... I'd be interested to know how well it works with an OpenAI or ZAI subscription.

▲

riedel 2 days ago | parent | prev [-]

I like it a bit for the inspiration what could make sense, however, as there is little ablation studies, it is really difficult to understand the effect of most of the features.