Claude Code Projects Adds Multi-Agent Cloud Threads — 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 in beta, letting users coordinate multiple AI agents under a single project with shared memory, goals, and a library of files and artifacts.
- Each project runs parallel 'threads' directed by a 'coordinator,' a pattern compared to Grok Bot and similar multi-agent management tools.
- Threads operate as independent cloud sessions on separate branches and repo copies, with overlapping code resolved as standard merge conflicts.
- Threads can recursively split their work using subagents, loops, and workflows to complete large assignments faster.
- Anthropic says local tools and code support are 'coming very soon'; beta access begins today for select Claude Pro and Max subscribers only.
- Access will later expand to all Pro, Max, Team, and Enterprise users, plus Cowork and regular Claude chats.
Why it matters: Power users on Claude Pro and Max get first crack at coordinated multi-agent coding in beta, with the rest of paid tiers and Cowork queued behind them. The architecture — separate branches per thread, merge conflicts handled like any PR — means parallel agent work now runs on primitives developers already understand rather than a black box.
Ask SkimNews
