Claude Code has relaunched its Projects feature to support running multiple AI agents together in the cloud. Within a project, agents share memory, goals, and a common library of files and artifacts. Work is organized into “threads” that run different tasks in parallel, with a “coordinator” directing the overall effort. Under the hood, each thread operates as a Claude Code cloud session working on its own branch and copy of the repository. When threads modify the same code, the overlap is handled as a merge conflict, similar to a standard pull request. Each thread can also further split its delegated work. The feature is compared to Grok Bot and other tools designed to manage groups of AI agents.
Why it matters
Coordinating multiple agents on parallel tasks within a shared context addresses the challenge of managing overlapping work, using familiar version-control conventions like branches and merge conflicts.
Who should care
Developers and teams using Claude Code for coding tasks who want to delegate and coordinate work across several agents at once.