You don't need to quit AI.
You need it to be closed sometimes.
LessLLM is a macOS menu bar app that blacks out AI chat services on a schedule you set — enforced at the DNS level by a system daemon, not an honor-system browser extension. Less LLM, not no LLM.
Scheduled blackouts
Weekends. After midnight. Whenever you keep promising yourself you'll stop. Recurring windows that turn the chatbots off without asking how you feel about it.
Real enforcement
A root daemon sinks DNS for the blocked services. New tab, new browser, app reinstall, reboot — still blocked. Quitting the app doesn't lift it either.
You hold the keys. Sort of.
You choose how hard each block bites — from a nudge you can wave off to a self-ransom that costs real money to break.
How it works
Pick which services go dark — ChatGPT, Claude, Gemini, Grok — and when.
When a blackout starts, running AI apps are quit after a short countdown — not so you can rush to finish, but so the stop lands as a deliberate breath instead of a jolt. There is never a good time to stop; that's the point. At worst you lose a minute of chat scrollback. For the rest of the window, DNS lookups for the blocked providers are refused at the system level. The daemon remembers its state: restarting the app, or the whole machine, lands you right back in the blackout you scheduled. The only doors out are the ones you chose ahead of time, and they're labeled by severity.
What gets blocked
The exact services, domains, and apps — straight from the source code, not a docs page that can rot.
-
Gemini & Antigravity
gemini.google.com,generativelanguage.googleapis.com,aistudio.google.com,makersuite.google.com,appsgenaiserver-pa.clients6.google.com,cloudcode-pa.googleapis.comApps quit at blackout start:com.google.antigravity,com.google.antigravity-ide -
ChatGPT, OpenAI & Codex
openai.com,chatgpt.com,oaistatic.com,oaiusercontent.comApps quit at blackout start:com.openai.codex -
Claude & Anthropic
anthropic.com,claude.ai,claudeusercontent.comApps quit at blackout start:com.anthropic.claudefordesktop, Claude Code (CLI) -
Grok (xAI)
grok.com,x.ai
This list is generated from the app's source — the same definition the DNS sink and app-quit logic use — so it can't drift from what actually gets blocked. Domains are blocked with all their subdomains.
Missing something? The app has a "Report a Coverage Gap" button that tells us exactly which domain slipped through.
The severity ladder
- Gentle Nudge A speed bump. The block is advisory and you can end it with one click. For people whose problem is momentum, not willpower.
- Hard Stop & Think Blocks for real, but you can write your way out: a short reflection on what you're reaching for and why right now. The questions are chosen deliberately — answering them tends to build the mental pathways that lead away from the chatbox, or at minimum toward a clearer understanding of why you keep ending up there.
- Serious AF Self-Ransom Blocks automatically. The only early exit is paying the penalty you chose when you set the block up — an option to add negative reinforcement to the decision matrix, at the exact moment you're weighing whether to violate your own blackout.
Self-ransom pricing
When you set up a self-ransom block, you choose what breaking it costs you. If you pay, the block lifts — that's the product: an early use penalty, sold to you, by you. Payments are processed by Stripe.
A non-zero amount of money is required to start using LLMs again. The app itself is free; you only ever pay yourself out of your own lock.
The honest version of the pitch
Sure — if you're determined enough, you'll figure out how to get around the blocks in a pinch. But you'll be doing it without LLM tools, so good luck with that. And every minute you spend trying to subvert the rule is a minute you didn't spend with an LLM — which was the goal. The block wins either way.