Claude Code projects now coordinate parallel work across threads

Anthropic has redesigned Claude Code projects so users can describe a goal and have Claude manage the work across multiple threads. Claude scopes the request, delegates work, coordinates parallel threads, reviews outputs, and assembles the finished result, while users can steer progress even from a phone and after stepping away.

Beta rollout

Starting today, updated projects are available in beta to select Claude Pro and Max subscribers who use cloud sessions in Claude Code and do not have existing projects on the web or desktop. Over the coming week, access expands to more Claude Code users on those plans, with updated projects across all of Claude and Team and Enterprise plans coming after that. Existing projects on Pro and Max plans keep working as they do today, and users without access can join a waitlist.

Threads and coordinator

Projects have threads that do the work and a coordinator that directs them. When starting a project, users select a goal and a repo or context, and Claude suggests work it can pick up right away. Users can configure the project's cloud environment, connectors, plugins, instructions, and model, then monitor and guide progress in the main project chat or in each thread.

With repositories connected, a thread opens pull requests and runs tests; with documents, it reads them and drafts. Each thread is a Claude Code cloud session working on its own branch and copy of the repo, and overlap on the same code is resolved as a merge conflict. Threads can also split delegated work into subagents, loops, and workflows.

Shared memory and library

Projects are designed for long-running or agentic workflows with more than one part. Every thread adds to and draws from shared memory, so Claude can remember details such as schedule changes or who to check with before touching a service. Claude also remembers the user's working and communication style, and projects include a library that collects files and artifacts produced by Claude.

Usage and what comes next

Because several threads can run at once, projects can reach usage limits faster. Users can check project-specific usage and select model and effort levels for the coordinator chat and worker threads. Threads run in the cloud today, while running on a user's machine alongside local tools and code is coming very soon.

Sources: claude.com · alphasignal.ai