Claude Code relaunches Projects for managing cloud AI agents

Anthropic is relaunching Projects in Claude Code as a way to manage multiple AI agents in the cloud. Each project includes shared memory, goals, and a library for files and artifacts.

The feature organizes work into “threads” that handle different tasks in parallel. A “coordinator” directs the work across those threads. Anthropic says each thread is a Claude Code cloud session with its own branch and copy of the repository. If threads change the same code, the overlap is handled as a merge conflict, like any other PR.

Threads can also divide delegated work with subagents, loops, and workflows when needed. Users can work with each thread separately or monitor and update them through the main project chat.

Threads run in the cloud at launch. Anthropic says support for local tools and code is coming “very soon.” The updated Projects feature is available in beta starting today to “select Claude Pro and Max subscribers.” Access will later expand to all Pro, Max, Team, and Enterprise users, as well as Cowork and regular Claude chats.