Anthropic has redesigned the Projects feature in Claude Code, allowing users to run multiple AI agents in parallel while sharing the same memory, goals, files, and artifacts.
Each project can contain multiple threads, with individual threads handling different tasks at the same time. A central coordinator keeps the overall project organized and directs the work.
Each Thread Runs Its Own Claude Code Session
Under the new system, every thread operates as a separate Claude Code cloud session with its own branch and copy of the repository.
This allows several agents to work independently on different parts of the same project.
If multiple threads modify the same code, any overlap is handled through a merge conflict, similar to conflicts that can occur when merging conventional pull requests.
Individual threads can also divide their assigned work further using subagents, loops, and workflows, allowing larger tasks to be completed more quickly.
Users Can Control Threads Individually
Users can interact directly with each thread if they want to monitor or change a specific task.
They can also manage progress and provide updates through the main project conversation, where the coordinator keeps track of the broader workflow.
The setup is similar to other systems designed to manage groups of AI agents, with several agents working simultaneously under a central coordinating layer.
Local Tool Support Is Coming
At launch, Claude Code project threads run in the cloud.
Anthropic says support for local tools and local code is coming “very soon.”
The redesigned Projects feature is available in beta starting today for select Claude Pro and Max subscribers.
Anthropic plans to expand access later to all Pro, Max, Team, and Enterprise users, as well as to Cowork and regular Claude conversations.
The post Claude Code Can Now Run Multiple AI Agents Simultaneously appeared first on ProPakistani.
