Claude Code relaunches Projects to manage multiple AI agents in the cloud

Anthropic updated the Projects feature in Claude Code: users can now run multiple agents in the cloud with shared memory, goals, and a file library. Each project is divided into 'threads' coordinated by a separate agent; the beta is available to select Pro and Max subscribers.

• Project unites multiple agents with shared memory and goals
• Each thread is a cloud Claude Code session on its own repository branch
• Code conflicts are resolved like merge conflicts in a PR
• Beta open to select Pro and Max subscribers, later to all