
Paul Domanski
116 posts

Paul Domanski
@domanski_ai
I install AI agents inside real jobs. Not next to people, in them. Founder, https://t.co/bAqmNxR8ki. Posting the builds: real installs, real numbers, from Cape Town.
Cape Town Katılım Mayıs 2026
104 Takip Edilen96 Takipçiler
Sabitlenmiş Tweet

"You've hit your usage limit."
Then you burn ten minutes logging in and out of your other accounts trying to find one with anything left in it.
I got tired of that and built headroom.
Every Claude and Codex account you own, on one live dashboard. It reads all of them without spending a single token. The moment one hits a wall, it rotates you to the next account that still has room.
Free. MIT.
How many accounts are you juggling right now?
English

@AnalyticsGenius For sure. But I do feel like Fable is able to claw its way back into my good graces a lot faster.
English

@domanski_ai Except they do retarded stuff like always even fable 5
Codex had compaction nailed
Claude has selective amnesia
English

@GaelBreton The tragedy is that Fable actually is so far beyond the other models. We’ve touched something special and it may be a while until we do so again.
I hate to use a word that’s been applied so mindlessly but Fable has “soul”.
English


@thsottiaux @jxnlco The great thing is that when Opus 5 is ready Anthropic are going to have to throw so much usage at us to catch up. 50% Fable has won them less Davor than they expected.
English

Hello. We have reached 8M active users across Codex and ChatGPT Work.
We are once again resetting the usage limits for all. And we continue to not have the 5h rate limit as well, allowing everyone to explore the boundaries of GPT-5.6 Sol and discover how ambitious you can be.
See you tomorrow for more updates on our growth!
Sam Altman@sama
5.6 sol growth is insane. the inference team has done heroic work to be able to support demand. we are going to move mountains to continue to scale, but it is possible there are some hiccups soon.
English

@demishassabis Can a body funded by the labs, watching for deception in models they profit from, ever be the one to say stop?
English

@noexistance92 @JonBuildsHQ Made using Claude design with Fable and the animation preset.
English

"You've hit your usage limit."
Then you burn ten minutes logging in and out of your other accounts trying to find one with anything left in it.
I got tired of that and built headroom.
Every Claude and Codex account you own, on one live dashboard. It reads all of them without spending a single token. The moment one hits a wall, it rotates you to the next account that still has room.
Free. MIT.
How many accounts are you juggling right now?
English

@AnalyticsGenius Fixed: headroom now carries your last verified reading through the throttle window
English

@domanski_ai maybe i should post this to git, but i started this here :)
Small followup - Because the rate limit check is rate limited itself- headroom refuses to launch instead errorring "[headroom] no account for 'claude' has proven headroom; try `headroom status claude`"
English

Found it and it's fixed on master: headroom read the cached Claude token and never checked expiry.
To unstick right now, run one Claude Code turn on that account - the CLI refreshes its own token and the next poll recovers.
Or pull latest: it now holds with a clear "token expired, run a turn or headroom connect" note instead of going dark. Thanks for the report.
English


@AnalyticsGenius Thanks for the heads up! Looking into it now.
English

@zdogmode Usage tracking and account rotation for AI power users. Fully open source:
github.com/domanski-ai/he…
English

@attacomsian Following!
Here we go:
github.com/domanski-ai/he…
English

@domanski_ai Love it. how can I access it?
p.s. let us connect too :)
English

@alex_prompter I can't fix the AI companies but I built something that could help a bit! It now features auto-rotation so your CLI sessions will move to the next account with capacity if you hit limits.
github.com/domanski-ai/he…
English

I spend more time tracking my usage limits than actually using Claude.
Weekly credits. Sonnet limits. Opus limits. Fable credits. 5-hour windows. Temporary increases that last "a few more days."
The rules change every other week.
I've been building AI workflows for 50+ clients. Claude is the best model I've used. And being a paying customer has become genuinely stressful.
Not because the model is bad. The model is incredible.
Because I'm constantly doing mental math on whether I can finish my work before I hit a wall.
It's like watching your phone at 8% during an important call. That low-battery anxiety. Every single day.
"Compute is expensive."
Yeah. We know. But that's your engineering and pricing problem. Not something you convert into daily stress for the people paying you.
Right now, Claude Pro feels less like a subscription and more like a rationing system.
We don't want credits we need a calculator to track. We don't want limits that change every Tuesday. We don't want "temporary increases."
We want to pay, open the app, and work.
That's the whole ask.
If AI companies don't solve this now, the entire industry is heading somewhere ugly: users spending more cognitive energy managing AI quotas than using AI to work.
Fix it while it's early @AnthropicAI.
English

@AnalyticsGenius I’m building out the desktop taskbar and widgets first then I’ll port to iPhone.
English






