Anthropic launches Claude Code Projects with parallel AI agents and shared memory
Anthropic announced a redesign of Projects in Claude Code, shifting to conversational coordination where users set goals and Claude autonomously breaks down tasks, coordinates parallel execution threads, reviews outputs, and aggregates results. The feature includes shared memory and a file library that accumulate over time, enabling persistent context across sessions. It is rolling out in beta to select Pro and Max users via waitlist, with broader availability expected later.
Reference imageEditorial 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: Claude Code now retrieves project instructions from AGENTS.md if CLAUDE.md is absent
Anthropic announced that Claude Code, its AI coding agent, can now retrieve project instructions from an AGENTS.md file if a CLAUDE.md file is not present. The post suggests this is part of a broader trend toward standardization, noting that it is inevitable that most common coding AI agents will eventually work on the same repositories and will need to find ways to collaborate more effectively. The announcement implies a move toward interoperability between different AI coding tools.
Claude Code adds AGENTS.md support with fallback to CLAUDE.md
In a post on X, addyosmani announced that Claude Code, an AI-powered coding assistant, now supports AGENTS.md configuration files. The tool will fall back to AGENTS.md if the CLAUDE.md file is not specified by the user. This update provides users with more flexibility in configuring the AI agent's behavior for coding tasks. The announcement was brief and did not include additional details about the feature's capabilities or release timeline.
Claude Code adds AGENTS.md support as fallback when no CLAUDE.md is present
Anthropic's Claude Code, starting in version 2.1.277, now supports AGENTS.md files. If a folder does not contain a CLAUDE.md file, Claude will automatically check for and use an AGENTS.md file instead. Users can toggle this fallback behavior in the /config settings. The update is effective immediately as of the announcement.
Read sourceShow 7 older updatesHide older updates
Anthropic announces Projects for Claude Code, rolling out to Pro and Max users via waitlist
Anthropic has officially announced Projects for Claude Code, a new feature that will be rolling out to selected Pro and Max users via 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 up required threads to run in parallel. A new overview panel will help users control the process and monitor responses that require follow-up. Claude Code Projects also feature shared memory, allowing them to serve as an evolving context. The source, testingcatalog, expresses curiosity to test the feature, noting it has been in development for a while.
Read sourceAnthropic launches Claude Code Projects with always-on AI agents for development work
Anthropic has launched a new feature called Claude Code Projects, now available in beta, which introduces an 'always-on' conversational interface that can remember context and delegate long-running development tasks to multiple AI agents in the cloud. The feature allows developers to manage multiple AI agents working in parallel on complex projects. Coverage from VentureBeat, The Verge, and DevOps.com highlights the capability for parallel AI work and cloud-based agent management. However, The New Stack warns that the feature could rapidly consume usage quotas, potentially draining a user's plan before lunch. The feature is part of Anthropic's ongoing expansion of its Claude AI platform for software development workflows.
Read sourceAnthropic's Claude Code release enables parallel task coordination with shared memory
A user on X praised a new release of Claude Code, stating that Claude can now coordinate parallel tasks from a single conversation. 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 that this would help the project get back on track. The post is attributed to user kimmonismus and reflects their opinion on the product's capabilities and desired improvements.
Projects brings Claude Tag's agent architecture to Claude Code with per-project memory
A new feature called Projects has been introduced for Claude Code, bringing the architecture of Claude Tag to the coding assistant. The feature assigns one agent per project that manages memory and spawns subagents for 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 represents a significant enhancement to Claude Code's capabilities by introducing persistent, project-specific agent memory and task delegation.
Claude Code rolls out Projects feature for select Pro and Max users
Anthropic's Claude Code is rolling out a new feature called Projects, as announced on X by addyosmani. A Project is described as an ongoing conversation that coordinates a stream of related work. Users describe a goal, and Claude splits it into threads, runs them in parallel in the cloud, and continues processing even after the user closes their laptop. The rollout begins today with select Pro and Max users on cloud sessions.
Claude Code launches parallel project threads that run after laptop is closed
Anthropic announced a new feature for Claude Code, its AI coding assistant, now in beta for select Pro and Max users in cloud sessions. The update allows projects to be managed from a single conversation, where users describe what needs to be done and Claude directs parallel threads that continue working even after the user closes their laptop. The feature is currently available in beta for select Pro and Max users and is expected to roll out to all Claude users soon. This development represents a significant advancement in AI-assisted software development, enabling persistent, asynchronous task execution.
Anthropic Revamps Claude Code Projects with Parallel Threads and Shared Memory
Anthropic announced a redesign of Projects in Claude Code, shifting from a folder-based approach to conversational coordination. In the new system, users set high-level goals, and Claude autonomously breaks down tasks, coordinates parallel execution threads, reviews outputs, and aggregates results. Each thread operates as an independent Claude Code cloud session, capable of running tests and opening pull requests on its own branch. The revamped Projects feature shared memory and a file library that accumulate over time, enabling persistent context across sessions. The official documentation details the thread coordination mechanism, shared memory functionality, and push cadence, allowing readers to evaluate whether to join the waitlist. This update represents a significant enhancement to Anthropic's AI coding assistant, moving toward more autonomous, multi-threaded project management within the Claude ecosystem.
Read source