Anthropic launches Claude Code Projects with persistent parallel threads in beta
Anthropic announced Projects for Claude Code, a beta feature enabling persistent, asynchronous AI-assisted project execution. Users describe tasks in a single conversation, and Claude directs parallel threads that continue running in the cloud even after closing a laptop. The feature assigns one dedicated agent per project with shared memory, coordinating subagents for complex multi-step coding tasks. It is initially rolling out to select Pro and Max users via a waitlist, with broader availability planned.
Editorial responsibility
- No named human review is recorded for this page.
- Reports are grouped by semantic similarity and deterministic rules. Language models may assist titles, summaries, translation and cross-source analysis; the page reads the event directly, while its address stays stable when the title changes.
- Summary covers the current reports
Cross-source coverage
Reporting timeline
Anthropic announces Projects for Claude Code with waitlist rollout for Pro and Max users
Anthropic has officially announced Projects for Claude Code, a new feature that will initially roll out to selected Pro and Max users under a waitlist, with a broader rollout to all Pro and Max users expected later. The feature allows users to start Projects from a conversation, enabling Claude to spin required threads to run in parallel. A new overview panel will help users control the process and monitor responses that require follow-up. Additionally, Claude Code Projects include a shared memory feature, allowing it to be used as an evolving context. The announcement was made via a post on X by the account testingcatalog, which expressed curiosity to test the feature, noting it has been in development for a while.
Read sourceAnthropic's Claude gains parallel task coordination and cloud persistence in Claude Code
A user on X praised a new release of Anthropic's AI model Claude, stating it can now coordinate parallel tasks from a single conversation starting in Claude Code. The system distributes work across threads that share project memory and continue running in the cloud even after the user closes their laptop. The post also expresses anticipation for a future Opus 5.2 release, which the user hopes will be less lazy and less verbose, suggesting a return to form for the model.
Anthropic Restructures Claude Code Projects with Multithreading for Parallel Task Execution
Anthropic has restructured the Projects feature in Claude Code, its AI coding assistant. According to the company's official documentation, the updated feature allows users to set goals, after which Claude breaks down tasks, orchestrates multiple threads in parallel, reviews outputs, and aggregates results. Each thread operates as an independent branch of a cloud-based Claude Code session. The restructuring introduces a coordinator plus multithreading approach to handle long-running tasks more efficiently. Anthropic has also provided details on the rollout scope and usage limits, enabling users to assess whether the feature fits their existing workflows. This update aims to improve the handling of complex, multi-step coding projects by leveraging parallel processing within the AI tool.
Read sourceShow 2 older updatesHide older updates
Projects brings Claude Tag's agent architecture to Claude Code with per-project memory
A new feature called Projects has been introduced to Claude Code, bringing the architecture of Claude Tag to the platform. The feature assigns one dedicated agent per project that manages memory and spawns subagents for specific tasks. Users can configure the agent to be proactive and perform actions on a schedule. The post describes the experience as much nicer than juggling multiple sessions and encourages users to try it. This development represents an enhancement to Claude Code's project management capabilities by introducing persistent, task-oriented AI agents.
Claude Code launches project management with persistent parallel threads in beta
Anthropic announced a new feature for Claude Code, its AI-powered coding tool, now in beta for select Pro and Max users. The update allows projects to be managed from a single conversation, where users describe tasks and Claude directs parallel threads that continue working even after the user closes their laptop. The feature is currently available in cloud sessions for a limited set of users, with a broader rollout planned for all Claude users in the future. This development marks a significant step toward persistent, asynchronous AI-assisted project execution.