Vibeleaderboard
← All Intel
Intel / post

Cua Previews Background Agent Input Isolation on Wayland

Source
Cua
Date
Cua@trycua
Thread · 5 parts

1/ At yesterday's Omarchy SF Meetup, we demoed a technical preview: an agent working across apps in the background with true multi-synthetic pointer. We'd like to work with the Hyprland community on native support for isolated background input. Here's what we have in mind.

2/ Here's @francedot demoing it live at the Omarchy SF Meetup at Cloudflare's SF office - running directly from Cua Fleet: https://t.co/8TodS4I5Ku

3/ We tested two compositor-side isolation paths: deliver directly to the target window's wl_pointer resource, or give automation a separate wl_seat. Both keep agent input away from the user's pointer-focus state and preserve the foreground drag.

4/ Both compositor approaches kept a real foreground drag intact during background delivery. As a next step, we're going to wire this in Cua Driver end to end, rebuild the current keyboard branch, resolve Chromium/Wayland behavior, and finish EIS device creation in the portal/libei path.

Read the full thread on X
Key takeaways · AI-distilled
  • Cua tested two compositor-side ways to isolate input on Wayland: deliver events directly to the target window's wl_pointer resource, or give automation its own wl_seat. Both kept agent input away from the user's pointer-focus state and left a real foreground drag intact.
  • Cua's remaining work before this is usable end to end: wire it through Cua Driver, rebuild the current keyboard branch, resolve Chromium/Wayland behavior, and finish EIS device creation in the portal/libei path.
  • Cua proposes that native Hyprland support start with an RFC defining permissions and a threat model and choosing the compositor contract, followed by Cua Driver integration, test coverage, upstream compositor PRs and a staged rollout. It remains a technical preview.
Terms in this piece · Glossary
  • AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters

Background, non-disruptive input control is a real blocker for practical computer-use agents on Linux; this lays out a concrete compositor-level approach and an RFC path toward native support.

More from Cua
Recommended reads
Comments

Checking sign-in…

Loading comments…