We're introducing Cursor Automations to build always-on agents.

Cursor can now continuously monitor and improve your codebase. Automations run based on triggers and instructions you define.

Cursor to software engineers:

Very cool launch! There's also an open source version of this

Y'all are becoming OpenClaw 🦞

Great, now my code can break automatically while I sleep.

@imjaredz this is crazy! also we are really in X bubble of anons underestimating cursor over CC/codex tbh

Slept like a baby last night Woke up to my Cursor Automation already: • Fixed 3 bugs I’d been ignoring • Refactored that spaghetti file • Updated every dependency • Wrote the tests Always-on agents aren’t a feature… they’re the employee of the month who never sleeps or asks for a raise. I’m not a developer anymore. I’m middle management for AI. @cursor_ai y’all are actually cooking 🔥

peak

With new release my workflow makes more and more sense:

This is sick! The team has been shipping amazing features super quickly, love to see it

woah super cool @jack_pertschuk

OK CURSOR IS COOKING

When Cursor drops a new update it just feels like Apple is the one dropping it Love ya guys 🫶

huge release, this is great

i did first haha

LETS FUCKING GOOOO

Love this! So many ideas and things to automate!

Another release?? running up against notion custom agents now... this is so useful 👀

@leerob W

Always-on credit consumption

I might be missing it. How does it know which environment to use when you have multiple repos?

The gap between "AI coding assistant" and "AI that runs your codebase while you sleep" just closed. Background agents that trigger on events, not prompts, is the real unlock. The question is whether teams trust it enough to let it merge without review.

building software went from writing code to telling AI to write code to now just setting up triggers so the AI decides when to write code. the human is becoming the exception handler

So, my AI can now run tasks automatically in the background with the new feature. Quite impressive

great name choice friends

the interesting thing about "always-on" agents isn't the automation — it's that they accumulate context over time. a one-shot agent is just a fancy function call. an agent that's been watching your repo for weeks understands intent, not just instructions. that's the real unlock here.

OpenCursor

What's the trigger mechanism for these automations? Are they responding to specific events or running on schedules? Curious how you handle the context handoff between autonomous actions.

Everyone is becoming openclaw in disguise

Great, now my code can break automatically while I sleep

Always-on agents that monitor and improve your codebase automatically? This is the future of dev workflows. Huge step toward truly autonomous coding environments 🔥