Claude Code Projects relaunches with multi-agent cloud control — SkimNews
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Claude Code relaunched its Projects feature, letting users run multiple AI agents under one roof with shared memory, goals, and a common library of files and artifacts.
- Each project runs parallel "threads" directed by a "coordinator," with overlap between threads resolved as standard merge conflicts — similar in concept to Grok Bot and other multi-agent tools.
- Under the hood, every thread is its own Claude Code cloud session on a separate branch with its own copy of the repo, and can further split delegated work into subagents, loops, and workflows.
- At launch, threads run in the cloud only, but Anthropic said support for local tools and code is coming "very soon."
- The beta is available starting today for select Claude Pro and Max subscribers, with access set to expand to all Pro, Max, Team, and Enterprise users — plus Cowork and regular Claude chats — later.
Why it matters: Anthropic is moving Claude Code from a single-thread coding assistant into a multi-agent project manager, competing directly with tools like Grok Bot. The tiered rollout means Pro and Max subscribers get first access, while Enterprise and Team tiers — often the biggest-paying customers — wait for general availability, making the "very soon" local-execution promise the key gating factor for adoption.
Ask SkimNews
