Anthropic says OpenClaw-style Claude CLI usage is allowed again

Post by OG_BME » Tue, Apr 21, 2026, 1:54 PM UTC

Post by Wowfunhappy » Tue, Apr 21, 2026, 2:22 PM UTC

filleokus wrote: post #72

stingraycharles wrote: post #59

Earlier quoted context omitted.

No, it's just that it's confusing, because there are two ways of using Claude Code credentials: 1. Take the oauth credentials and roll your own agent -- this is NOT allowed 2. Run your agentic application directly in Claude Code -- this IS allowed When OpenClaw says "Open-Claw style CLI usage", it means literally running OpenClaw in an official Claude Code session. Anthropic has no problems with this, this is complia…

But... Even when running it in mode 2 ("claude -p") they at certain points tried to detect OpenClaw-usage based prompts made, and blocked them [0]. Now OpenClaw says that Antrophic sanctions this as allowable again. I agree with GP that this is hard to take seriously. [0]: https://x.com/steipete/status/2040811558427648357

Post by LatencyKills » Tue, Apr 21, 2026, 2:33 PM UTC

doginasuit wrote: post #185

LatencyKills wrote: post #135

Earlier quoted context omitted.

Many people likely objected to the original restriction because it seemed as though Anthropic was trying to impede the development of competing tools. If I'm paying for compute, why should it matter whether I use Anthropic's harness (e.g., Claude Code) or a 3rd-party harness?

I find it a little bizarre that people have this expectation. You can still pay for compute and use it the way you want by paying for the product you actually want to use. Subscription products like this are not marketed or intended to be used as access to the API, but they also offer access to the API if that's what you want. I'm still not entirely clear why people insist on using their subscription like this, so le…

Post by joelmanner » Tue, Apr 21, 2026, 2:38 PM UTC

Scotchy wrote: post #12

redrove wrote: post #10

Earlier quoted context omitted.

I’ve been using Codex Pro since they lobotomized Opus 4.6. Codex is so much better, GPT 5.4 xhigh fast is definitely the smartest and fastest model available. For a while there I had both Opus 4.6 and Codex access and I frequently pitted them against each other, I never once saw Opus come out ahead. Opus was good as a reviewer though, but as an implementer it just felt lazy compared to 5.4 xhigh. One feature that I h…

Any alternative to Claude Design ? Tried Figma with Opus 4.6 but it doesn't come close in my experience. Codex is abysmal for UI design imo.

Post by wafflemaker » Tue, Apr 21, 2026, 2:43 PM UTC

ToucanLoucan wrote: post #184

gavinray wrote: post #182

Earlier quoted context omitted.

I pay the $20 sub for all of the Frontier models and just hop between them as performance changes I will say that Codex high/x-high has consistently performed the best for me, but YMMV

See the thing is their storefront is so fucking vague. Right now I hit usage limits after about 4-6 messages during the day, depending on length. They say the low tier is 5x usage, so does that mean I can send 20-30 messages? Because that's not remotely worth $20 a month to me.