[okrad]

I believe Codex harness is pretty sticky though I haven’t tried many others. Does anyone else provide a harness of that quality?

[nvarsj]

Pi harness with subagents is pretty great. I’m using it for everything now.

[yeswecatan]

How are you handling subagents?

[nvarsj]

tintinweb/pi-subagents. Then I use superpowers and it spins up subagents automatically. Works really well and you can customise the models and efforts you want to use with local AGENTS.md.

I’m primarily using gpt-5.6 and then opus for reviews.

[RALaBarge]

You say hey llm spin up some agents to do x y and z

[anderber]

Usually the main agent can handle creating subagents

[conradludgate]

Their harness is indeed nice, but we're using it against our own AI Gateway at work. Right now we only expose GPT models on it, but I imagine it's possible to add our own models eventually

[verdverm]

opencode is highly regarded, I use it exclusively

[Roark66]

Open code is cool once I added the ctrl-o function to it (show thinking and command outputs at will instead of on by default), but sadly I don't think it got merged by the team.

I forgot why.

But I can't use an AI cli without that feature.

[verdverm]

you can turn those on through the existing menu system

[versteegen]

...but we're talking about compaction, and opencode's compaction is (or was) terrible. I've seen so many horrible problems that I keep it disabled (with an envvar flag, because even the config flag to turn it off was broken).

[verdverm]

I don't use compaction, I keep my context limited, my sessions fresh, and have agents write markdown files as needed

[jki275]

I've used open code extensively -- it's not bad, but it's not anywhere near the level of the codex application.