Claude Code revamps Projects for coordinating cloud-based AI agents
Claude Code’s revamped Projects feature lets users manage several AI agents within one project. The agents share memory, goals, and a library of files and artifacts, while separate threads handle different tasks in parallel. A coordinator organizes the work and directs the overall project.
Each thread runs as a Claude Code cloud session on its own branch and repository copy. If multiple threads modify the same code, their overlap produces a merge conflict handled like one in a regular pull request. Threads can also divide assignments further through subagents, loops, and workflows.
Users can open individual threads or follow progress and make changes through the project’s main chat. Cloud execution is available at launch, while Anthropic says support for local tools and code is coming “very soon.” The feature is initially in beta for select Claude Pro and Max subscribers. Access is planned to expand to all Pro, Max, Team, and Enterprise users, along with Cowork and standard Claude chats.
Written by Sakhanda Wire AI from reporting by The Verge. Facts, quotes and full context are in the original article below.