Anthropic adds Projects to Claude Code to coordinate multiple AI agents in shared workspaces

Anthropic is adding a Projects feature to Claude Code that lets users run multiple AI agents together in shared cloud workspaces. Each project provides a shared memory, goals, and a library of files and artifacts that all agents can access.

Within a project, users can spin up parallel threads, each running as an independent Claude Code cloud session on its own branch and copy of the repository. A coordinator oversees the threads, and when multiple threads modify the same code, overlaps are resolved as merge conflicts, similar to pull requests.

Threads can further decompose work using subagents, loops, and workflows to finish large assignments faster. Users can interact with individual threads or monitor and update progress through the main project chat.

At launch, threads run in the cloud, but Anthropic says support for local tools and code is planned for a future update. The feature is available in beta starting today for select Claude Pro and Max subscribers, with access expanding to all Pro, Max, Team, and Enterprise users later, as well as Cowork and regular Claude chats.