Anthropic has updated the Projects section in Claude Code, enabling multiple AI agents to operate within a single workspace. These agents collaborate by sharing memory, objectives, files, and artifacts to complete tasks simultaneously.
The system utilizes a coordinator agent to manage task distribution across separate cloud-based threads. Each thread functions as an independent Claude Code session with its own repository branch, while code conflicts are resolved similarly to standard pull requests.
Users can monitor progress through a main project chat or interact with individual threads. Currently, the feature supports cloud-based operations, with local tool and code support expected in the near future.
The updated workspace is currently available in beta for select Claude Pro and Max subscribers. Anthropic plans to roll out the functionality to all Pro, Max, Team, and Enterprise users, as well as Cowork and standard Claude chats.
