Claude Code Projects Beta: Cloud Threads Persist After Laptop Closes
Anthropic's redesigned Claude Code Projects shifts from static folders to an AI-coordinated thread system, but the most powerful features remain cloud-only for now.
Anthropic has launched a beta redesign of Claude Code Projects, replacing the old folder-plus-chat model with a single ongoing conversation where Claude acts as coordinator. Instead of manually managing files and one chat, you describe the work and Claude decides what becomes a thread, each thread being a full Claude Code session. This shift turns projects into dynamic, AI-orchestrated workflows rather than static containers.
The most striking feature, highlighted by MarkTechPost, is that these threads run as parallel cloud sessions that continue even after you close your laptop. That means long-running tasks can proceed without a developer keeping their machine on. ZDNET confirms this capability but adds a caveat: the biggest benefits are cloud-only for now, and local developers must wait for equivalent functionality.
Both sources agree the redesign is a significant step toward AI-managed coding workflows, with shared memory and cross-repo coordination. However, they differ in emphasis—MarkTechPost focuses on the persistence of cloud sessions, while ZDNET stresses the current limitation for on-premises users. The beta is available now, but its full impact depends on how quickly Anthropic extends these features beyond the cloud.
Sources · 3
More in AI & ML
Jev Creator on System One Models for Production, Not AGI
TypeSafe AI CEO Diogo Almeida, lead creator of Jev, argues System One models belong in production rather than on an AGI pedestal.
Meta's Muse AI Assistant Has a 0-Day That Lets Attackers Hijack It
A newly reported vulnerability in Meta's Muse AI assistant can be exploited with a simple ClickFix attack to take full control of the agent.
Pruning LLMs by Removing Blocks as an Ising Optimization Problem
A new approach frames large language model pruning as a physics-style Ising optimization to decide which blocks to remove.
NVIDIA: AI Security Needs Engineering, Not Just Policies
NVIDIA argues that securing AI agents requires treating security as an engineering discipline with requirements, controls, owners, and evidence.