Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers
Anthropic has updated Claude Code Projects, enabling a central AI coordinator to manage multiple parallel worker threads across complex software repositories.
Photo: Hacker News Front Page
Key points
- Anthropic updated Claude Code Projects to run multi-threaded AI workers coordinated by a central agent.
- Worker threads run in independent cloud sessions to edit repositories, execute tests, and open pull requests.
- The update is currently in beta for select Pro and Max users, with plans to expand to enterprise customers and self-hosted environments.
Anthropic has introduced an updated version of Claude Code Projects, adding the ability to run parallel AI worker threads that autonomously complete complex coding tasks. The update enables the AI system to act as a project manager, dividing large assignments across independent cloud sessions to streamline software engineering workflows.
Under the new setup, a central coordinator agent breaks down overall goals into sub-tasks and delegates them to individual worker threads. Each thread operates within its own cloud session on a dedicated code branch, executing tests, making modifications across different repositories, and opening pull requests. If separate threads modify overlapping files, the system handles the conflicts through standard pull request merge processes.
The upgraded projects feature also incorporates a shared memory system, allowing individual worker threads to store and reference project-specific details and user communication preferences over time. Additionally, a central library now collects project files and AI-generated artifacts for future reference across team tasks.
The updated feature is currently rolling out in beta to select Claude Pro and Max tier subscribers who use cloud sessions. Anthropic plans to expand access to additional individual subscribers in the coming week, followed by enterprise and team plan customers, alongside plans to launch self-hosted agent options for local and private cloud environments.
What to watch next: Anthropic plans to bring local machine execution to these parallel agents, allowing developers to run multi-threaded workflows behind enterprise firewalls.
Source Hacker News Front Page — claude.com/resources/articles/projects-redesigned ↗
Read next
⚖️Regulation & PolicyOpenAI Partners with Chilean Ministry to Advance Public Sector AI
OpenAI has signed a non-binding agreement with Chile's science ministry to integrate artificial intelligence into public administration and support local startups.
🌐Work & SocietyAmbience Healthcare Expands Clinical AI Suite for Hospital Operations
Ambience Healthcare has launched new AI tools designed to assist hospital staff with patient rounding and discharge planning, aiming to improve both clinical efficiency a…
🧠AI AnalysisAI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows
New research reveals that leading AI models from firms like OpenAI and Anthropic can be manipulated into identifying civilian targets when prompted with game scenarios.
⚖️Regulation & PolicyAWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026
Amazon Web Services is spotlighting its workplace AI platform, AWS Quick, ahead of its upcoming re:Invent 2026 conference, emphasizing secure deployment across major ente…
🏢Big TechLoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows
LoanPro has deployed a multi-agent AI assistant using Amazon Bedrock and Anthropic's Claude models to help lenders manage borrower accounts, resulting in a 15% reduction …
🏢Big TechGoogle Brings Wallet App to iOS Users Across the United States
Google has expanded the availability of its Wallet application to iOS devices in the U.S., allowing Apple users to store digital passes, tickets, and receipts.