Repeated cloud agent failures, going on 24h

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

For about 24 hours now, every attempt to start a cloud agent (approx. 10 or 12 tries) has been stuck on “setting up environment.” Only one of those times did I get an error, “We repeatedly ran into an error”, but the rest just indefinitely worked.

I’ve restarted, checked for updates, attempted to run them from the web interface, no dice. (Same model works fine on local.)

Steps to Reproduce

Start a cloud agent

Expected Behavior

The Cloud agent should execute the task

Operating System

MacOS

Version Information

Version: 3.4.20
VSCode Version: 1.105.1
Commit: 0cf8b06883f54e26bb4f0fb8647c9500ccb43310
Date: 2026-05-15T02:26:10.351Z
Layout: glass
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Darwin arm64 25.4.0

Additional Information

Cursor’s status page claims the issue was resolved approx 12 hours ago, but I’m still unable to utilize any cloud agents.

Does this stop you from using Cursor

Yes - Cursor is unusable

Hi @MishaTheMisha Sorry for the inconvenience. We currently have an active incident regarding degraded behavior for cloud agents. We are working on it! You can keep track of the status here: Cursor Status - Degraded behavior in cloud agents and automations.

Where does the bug appear (feature/product)?

Background Agent (GitHub, Slack, Web, Linear)

Describe the Bug

Cloud agents are failing to spin up today, they were working just fine yesterday. I started multiple sessions and have been waiting 10+ minutes for them to start.

Steps to Reproduce

Start a conversation with a cloud agent.

Expected Behavior

The conversation with the cloud agent starts

Operating System

MacOS

Version Information

Web

For AI issues: which model did you use?

Composer 2 & 2.5

Does this stop you from using Cursor

Yes - Cursor is unusable

Status page hasn’t been updated :frowning:

Yep, it erroneously says that it has already been resolved. But the entire day seems up and down…