On Oct 9 ClaudeDevs said every Pro and Max user on the Claude Code Projects waitlist has been let in. A project is a long-running coordinator conversation that spins each task into its own thread, usually a parallel cloud session on its own branch that opens a PR when needed; threads can also run locally via Remote Control. Still public beta; not yet on Team or Enterprise.

Key Takeaways

  • ✓From Oct 9, every Pro/Max user on the waitlist has access; still public beta, not on Team/Enterprise.
  • ✓A project is one coordinator conversation plus N threads, each with its own context window; cloud threads work on their own branch and open PRs.
  • ✓Since Sep 23, threads can run on your own machine via Remote Control when a task needs local tools.
  • ✓New threads inherit project instructions and memory, each repo's CLAUDE.md and skills, and your claude.ai connectors.
  • ✓Projects draw on the same plan limits as other Claude Code sessions and use them faster; no benchmarks were published.
🧭

Heavy Claude Code use: compare subscription limits and API bills

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Claude Code Projects, introduced Sep 17, is now open to every Pro and Max user who joined the waitlist (ClaudeDevs, Oct 9). A project is one long-running coordinator conversation: you paste bugs, stack traces or task lists, and Claude starts a thread per task or routes it to an existing thread. Each thread has its own context window and is usually a cloud session working on its own branch, opening a PR when needed; cloud threads keep running after you close your laptop, and since Sep 23 a thread can run on your own machine via Remote Control. Threads inherit project instructions and memory, each repo's CLAUDE.md and skills, and your claude.ai connectors. Anthropic published no benchmarks; the docs warn projects use plan limits faster than single sessions. Still public beta and not yet on Team or Enterprise.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextAnthropic opens multi-agent Code Review to Claude Code Team/Enterprise: substantive comments 16%→54%
Read Now→