Connect a GitHub repository so the AI can reference your code, structure, and history.
The GitHub connection gives the AI read access to a specific repository in your workspace. Once connected, the AI can answer questions about the codebase, reference file structure and content when generating briefs, and provide more relevant suggestions when your work involves code.
You connect one repository at a time. You can add multiple GitHub connections if your project spans several repositories.
GitHub uses a full sync model: data is indexed on connection and can be refreshed manually at any time from your connections page.
owner/repo format (e.g. acme/web-app)main)The connection appears in your active connections list and the data is indexed immediately.
You need a GitHub Personal Access Token (PAT) with the following permissions:
To create one:
The Connect GitHub dialog includes a direct link that pre-fills these settings for the repository owner you enter.
If your project spans multiple repositories, add a separate GitHub connection for each one. Give each connection a descriptive name so you can identify them on the connections page.
GitHub data is synced on connection. If significant changes have been made to the codebase since you connected, you can trigger a manual re-sync from the connections page to pull in the latest content.
Hamster validates token capabilities and shows warning badges when a GitHub token is missing key scopes (for example, push or pull request access). This helps you spot incomplete permissions before running workflows that depend on those capabilities.
main or develop, not a feature branch.