Cursor Cloud Agent fails with “Error loading default branch” during environment setup

Where does the bug appear (feature/product)?

Background Agent (GitHub, Slack, Web, Linear)

Describe the Bug

Description
I’m encountering a persistent issue when using Cursor Cloud Agent. During environment initialization, the setup fails with the following error:

Error loading default branch. Please try again later, or contact Cursor support at [email protected].

Because of this, I’m unable to create or initialize the Cloud Agent environment for the repository.

Actual Behavior
The agent fails during setup and shows:
Error loading default branch. Please try again later, or contact Cursor support at [email protected].

Steps to Reproduce

Open Cursor

Start a Cloud Agent for a GitHub repository

Let the agent initialize the environment

The setup fails with the error above

Expected Behavior
Cursor Cloud Agent should successfully load the repository’s default branch and complete environment initialization.

Operating System

MacOS

Version Information

Version: 2.6.13
VSCode Version: 1.105.1
Commit: 60faf7b51077ed1df1db718157bbfed740d2e160
Date: 2026-03-06T06:17:49.499Z
Build Type: Stable
Release Track: Default
Electron: 39.6.0
Chromium: 142.0.7444.265
Node.js: 22.22.0
V8: 14.2.231.22-electron.0
OS: Darwin arm64 25.3.0

Does this stop you from using Cursor

Yes - Cursor is unusable

Hey, this is a known issue. The GitHub installation token on our backend sometimes fails to resolve correctly, which causes the “Error loading default branch” error during Cloud Agent setup.

Several other users have reported the same thing:

The team is aware. No ETA yet, but reports like yours help with prioritization.

To help us debug on the backend, could you share:

  1. The Request ID from a failed Cloud Agent run (from the URL on cursor.com/agents)
  2. Which repo(s) are affected. Is it all repos in your org, or only specific ones?
  3. Have you tried reinstalling the Cursor GitHub App? (Note: this sometimes temporarily fixes things but isn’t reliable)

Unfortunately there’s no solid workaround right now. Retrying after some time sometimes works. Let me know if you can share those details.

This topic was automatically closed 22 days after the last reply. New replies are no longer allowed.