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

Anthropic has relaunched the Projects feature for Claude Code to let users manage multiple AI agents in a single workspace. Projects combine a shared memory and goals with a common library of files and artifacts so groups of agents can work toward unified objectives. Within each project, separate threads run tasks in parallel while a coordinator component organizes and directs activity.

Technically, each thread corresponds to a distinct Claude Code cloud session operating on its own branch and copy of the repository. When multiple threads modify the same code, overlaps are handled as merge conflicts similar to pull request workflows. Threads can also subdivide assigned work further by spawning subagents, using loops, or invoking workflows to accelerate completion of large tasks.

Users can interact with individual threads or monitor and make updates through a central project chat. At initial release, threads run in the cloud; Anthropic says support for local tools and local code access is coming "very soon." The revamped Projects feature is available in beta starting today for select Claude Pro and Max subscribers, with plans to expand access to all Pro, Max, Team, and Enterprise users as well as to Cowork and regular Claude chats in the future.

The announcement positions Claude Code Projects alongside other multi-agent management tools by providing built-in coordination, repository isolation per thread, and conflict-resolution behavior familiar to developers. The rollout begins with a limited beta and will broaden to additional subscription tiers over time.