Anthropic adds cloud project orchestration to Claude Code for select users

Claude Code’s revised projects adds AI orchestration, but local developers must wait

Image: Primary

Published Thursday, September 17, 2026 · 6:08 PM EDT

Anthropic said it is redesigning projects in Claude Code so the assistant can scope a request, delegate work across parallel threads, review outputs, and assemble a result, including after a user closes a laptop. The company said the capability is offered to select Claude Pro and Max subscribers who use cloud sessions and do not already have projects on the web and desktop; existing projects stay as they are for now. Each thread is a full cloud session with its own branch and repository copy, and Anthropic said threads share memory and can be steered while running. Local terminal workflows are unchanged, with on-machine threads described as coming later. Anthropic said projects reach usage limits faster because several threads can run at once.

Sources

ZDNET

In this story

Anthropic

Published by Tech & Business, a media brand covering technology and business. This story was sourced from ZDNET and reviewed by the T&B editorial agent team.

Back to Newswire

Keep reading

Full wire

AI Products

Nvidia reportedly requires cloud clients to direct 51%+ of services outside China

Nvidia verbally told cloud computing clients to sell 51%+ of their services to non-Chinese companies, the Financial Times reported, citing sources.

Security

Attackers target unpatched WordPress payment flaw that exposes wallet credentials

Attackers are attempting to exploit an unpatched vulnerability in the CryptoPayment Gateway WordPress plugin, Defused Cyber said. CVE-2026-81648 has a CVSS score of 10.0 and affects versions 1.2.1 through 1.2.2, the latest version.

Robotics

Tesla tests two dozen Cybercabs on Detroit-area roads

Tesla is testing two dozen Cybercabs from its Southfield facility on roads in the Detroit area, The Detroit News reported.

AI Science

Preprint reports agent context compression with up to 50.68% fewer attention pairs

Researchers report a method that matched or exceeded an uncompressed language-model agent's accuracy on long-running tasks while using up to 50.68% fewer end-to-end attention pairs, a measure of attention computation.

Claude opens message threads beta for long-running agents

Anthropic has opened message threads in public beta on the Claude Platform, letting agents send new messages without retransmitting their full conversation history.

Athenahealth connects patient records to paid Claude accounts

Athenahealth has launched AthenaPatient MCP, a server that lets Claude retrieve patient health records and answer questions about them, ZDNET reports. Access is limited to Claude Pro and Max subscribers, whose plans cost $20 and $100 per month, respectively.