What tools do you find are better?

I have been happy with Claude Code lately, but I haven't explored other options much in over a year. Curious to try something else out if it's less rambling and tangential.

▲ agentdev001 4 hours ago | parent | next [-]

> less rambling and tangential

This is not necessarily a problem with the harness (IE, swapping from Claude Code wouldn't necessarily fix this).

If what you're looking to avoid is specifically 'rambling and tangential', you can get quite far with anything that adds directives to avoid those things, early in every context window. Ie, through use of Agents.md/claude.md, skills, hooks, and so on.

Changing model would also affect this. Fable 5, Opus 5, and Sonnet 5 are all going to average out to different levels of ramble. Openai, Xai, Google, etc; different providers models will also have different levels of ramble.

What Claude Code does take away from you is some level of control over what makes it into the context window. The system prompt which claude code append to the beginning of every session of course has measurable ramble-affect.

I quite like the Pi harness, most in part because important goal with the approach behind it is "give the user as much control over what makes it into the cotext window as possible."

Codex TUI is also good. Haven't touched it since moving to Pi however. Again- harness isnt the big "stop rambling" thing to change, tho.

▲ epistasis 2 hours ago | parent | prev | next [-]

Pi with Claude is better than Claude code in my experience. But I even use old GLM5.2 with pi and generally have a better experience than current Claude Code. It reminds me of peak productivity with Claude Code of 5+ months ago.

▲ andai 4 hours ago | parent | prev | next [-]

The sub only works in Claude Code itself (unless they changed that rule again?), and all the Chinese models are trained on Claude Code (a bunch of them don't even work in Codex).

I use a custom harness, but I constantly hear good things about Pi.

EDIT: Checked out Pi and Oh-My-Pi. 250k LoC and 1.5M LoC respectively. Sheesh. How's that for minimalism...

Mine's 50. (Lines.)

https://gist.github.com/a-n-d-a-i/bd50aaa4bdb15f9a4cc8176ee3...

Vendored in my own LLM micro library (100 LoC) so it's 150.[0]

There's no parallelism or anything, but I use it for surgical edits and it's much faster and cheaper than the official harnesses for some reason. (Absence of sysprompt bigger than my repo probably helps there...)

[0] This one uses OpenRouter so you can use it with any model, but jerry rigged Codex sub version available on demand :)

---

I also have a ultra turbo bloated version (500 lines... need to strip it down a bit!) which has autorun files (for grep-based context injection), notification (frog croak when agent done, etc.) Watch this space!

▲ agentdev001 4 hours ago | parent [-]

They did walk that back, you are able to use an Anthropic login in a non-anthropic harness. (For now.)

(Edit: I failed too mention, using a different harness with a CC/Anthropic subscription bumps you up to the pay-per-token rate.)

▲ alanwreath 3 hours ago | parent | next [-]

Doing the whole “pay per token rate” when logging into a harness not made by them is not only being enforced by anthropic/claude though. It also is what Google does with agy (their TUI).

Is there any provider that doesn’t do this? That’s the one I want to support.

  > TLDR: they are all probably doing it because they are banking on you not using all your tokens.

I would be surprised though, it makes business sense to make the default vendor native TUI cheaper because it’s understood that most nascent users will just use the harness offered by the LLM provider and those that would stray off that would probably be more power users who would spend their token share more consistently till it drains.

	▲	agentdev001 3 hours ago \| parent \| next [-]
		OpenAI allows you to use the subsidized limits outside of their products. I don't think they clearly "tell" the world that this is the case, but they do put out a product surface that- I dont think they would, if they didnt allow this usage. This is... close. They offer ways to leverage openai subscription directly for 3rd party app use. https://learn.chatgpt.com/docs/app-server
	▲	areoform 3 hours ago \| parent \| prev [-]
		`> Is there any provider that doesn’t do this? That’s the one I want to support.` Yes, IIRC, OpenAI. In sama we trust??

▲ andai 4 hours ago | parent | prev [-]

Yeah and it bills extra usage? Or did they walk that back too.. gotta keep the customers on their toes!

	▲	agentdev001 3 hours ago \| parent [-]
		Shoot, yes. The user experience of logging in is the same, but yes- using a different (non-cc) harness bumps you up to the pay-per-token rates. However! I have seen projects which use CC under the hood, in order to get the subsidized rates. Writing comments which get me to go look through anthropic documentation, and find friction I wasnt aware of (CC does not have an app-server), refreshes my frustration towards anthropic.

▲ 8cvor6j844qw_d6 4 hours ago | parent | prev | next [-]

New guidelines that I have seen in a certain place is to configure and update existing CC setups to be CC/Codex agnostic. Plus setting up both allows Claude Code to delegate tasks [1] to Codex to reduce usage.

Most are easy to share with symlinks and @agents.

https://github.com/openai/codex-plugin-cc

	▲	andai 4 hours ago \| parent [-]
		Oh my god, that's an official plugin. That's hilarious. I had the same idea last year, when I noticed how much cheaper GPT was for the same tasks, but Claude was still better as a high level "operator". Also cause OpenAI was cool with you calling their sub in an automated way, but Anthropic very much was not (they were banning people at the time).

▲ cleaning 4 hours ago | parent | prev | next [-]

T3 Code if you want to use your subscriptions in an interface that respects its users.

▲ dalenw 4 hours ago | parent | prev [-]

Not OP but I like OpenCode a lot. But OhMyPi: https://omp.sh/ is also taking off. Personally I didn't like it as much as OpenCode.