# Better ability to switch back and forth between IDE and Cloud Agents

**URL:** <https://forum.cursor.com/t/better-ability-to-switch-back-and-forth-between-ide-and-cloud-agents/156358>\
**Category:** Feature Requests\
**Tags:** cloud-agents\
**Created:** [March 31, 2026, 8:23pm UTC](https://forum.cursor.com/t/better-ability-to-switch-back-and-forth-between-ide-and-cloud-agents/156358 "2026-03-31T20:23:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ryanw](https://avatars.discourse-cdn.com/v4/letter/r/839c29/32.png) [@ryanw](https://forum.cursor.com/u/ryanw)\
**Post date:** [March 31, 2026, 8:23pm UTC](https://forum.cursor.com/t/better-ability-to-switch-back-and-forth-between-ide-and-cloud-agents/156358/1 "2026-03-31T20:23:32Z")

</div>

### Feature request for product/service

Cursor IDE

### Describe the request

I would love a world where I can kick off a cloud agent from my phone, and then sit down at my desk and pull that in as a local session, exactly as if I’d started it in the IDE.

Or vice versa, build out a plan with an agent in the IDE, and then kick it to a cloud agent for implementation. I know there’s a (hard-to-find) “build in cloud” option for plans, but I tried it a few days ago and it didn’t seem to work, so I wasn’t sure if that’s even supported anymore. And it’s also a little unclear how it works and how much of the original context gets pushed to the new agent?

### Operating System (if it applies)

MacOS