Skip to content
NewA calmer, faster ZeroHour

Anthropic adds parallel workers and coordinator updates to Claude Code Projects

Original title: Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-Free

Hacker News · AIby toppa33 ()3 min read1
Part of a story covered by 2 sourcesAnthropic upgrades Claude Code Projects with parallel cloud workersMerged summary & timeline
AI summary · x-ai/grok-4.7Summaries by Vani AI

The public beta stays Pro and Max only, with a 200-thread daily cap and no separate fee.

Anthropic updated Claude Code Projects so a coordinator can assign work to independent cloud sessions, each with its own repository copy and Git branch. Coordinators now post status and pending decisions without prompting, and threads can be shared via read-only links unless they accessed a local computer. The update is on web, desktop, and the latest mobile app. Team and Enterprise plans remain unsupported, and workers draw from the existing Claude Code allowance.

Key facts
  • Public beta began September 17 for Pro and Max waitlist subscribers.
  • Accounts are limited to 200 new threads per day across projects.
  • New projects default to Opus, low effort for the coordinator and high for workers.
  • Local-access threads cannot be shared, to avoid exposing files or shell output.
  • Reminders, /btw, and /fork are now available inside Projects.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

3 min read at alphasignal.ai

Anthropic has updated Claude Code Projects with proactive coordinator messages, read-only thread sharing, reminders, branching commands, and improved artifact navigation. The changes reduce the monitoring required when several cloud sessions work in parallel. Each project is a long-running conversation with a coordinator that assigns work to threads.

Hacker News · AI

By toppa33 · alphasignal.ai

Read the full article at Hacker News · AI

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.