Anthropic Launches Claude Code Projects in Beta: Persistent Parallel Cloud Sessions for Agentic Coding

Anthropic has relaunched Claude Code Projects in beta, enabling developers to run multiple parallel AI coding sessions in the cloud that continue executing even after closing their local machine. This is a meaningful architectural shift — Claude Code is no longer tethered to an active terminal session, meaning long-running tasks like large refactors, test suite runs, or multi-file codegen can complete asynchronously. Developers can spin up multiple independent project contexts simultaneously, each maintaining its own state and tool access. This brings Claude Code closer to a true autonomous software engineering agent rather than an interactive assistant. Teams building on Anthropic's API should evaluate this for CI/CD integration and hands-off code generation pipelines.