# Allow for agents to communicate with each other

**URL:** <https://forum.cursor.com/t/allow-for-agents-to-communicate-with-each-other/148141>\
**Category:** Feature Requests\
**Created:** [January 6, 2026, 8:36pm UTC](https://forum.cursor.com/t/allow-for-agents-to-communicate-with-each-other/148141 "2026-01-06T20:36:11Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![deanrie](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/deanrie/32/1263_2.png) [@deanrie](https://forum.cursor.com/u/deanrie)\
**Post date:** [January 7, 2026, 10:23am UTC](https://forum.cursor.com/t/allow-for-agents-to-communicate-with-each-other/148141/3 "2026-01-07T10:23:35Z")

</div>

Hey, thanks for the request.

Multi-agent collaboration and orchestration is something users have asked for before, and the team is aware of the interest in this area.

For now, there’s a community solution worth checking out. You can run and orchestrate `cursor-agent` instances via the CLI directly from inside Cursor. See this recent post for details: How to Use Cursor-Agent from Inside Cursor IDE [This might help some folks with complex workflows: How to Use Cursor-Agent (and/or Claude-Code-SDK) from Inside Cursor IDE](https://forum.cursor.com/t/this-might-help-some-folks-with-complex-workflows-how-to-use-cursor-agent-and-or-claude-code-sdk-from-inside-cursor-ide/147954).

I’ll pass your specific use case to the team, like separating frontend and backend work for large repos.

---

_[View the full topic](https://forum.cursor.com/t/allow-for-agents-to-communicate-with-each-other/148141)._