3 Sources
[1]
Claude Code's revised projects adds AI orchestration, but local developers must wait - ZDNET
* Claude Code Projects could tame multi-agent chaos. * Cloud users get persistent threads and shared memory. * Local workflows remain outside the new system for now. Claude Code has always had projects, in the sense that a given directory is declared as the root for source code. I keep each of
[2]
Claude Code relaunches Projects to manage multiple AI agents in the cloud
The revamped projects feature in Claude Code allows users to run multiple agents under the same roof, with a shared memory, goals, and library of files and artifacts. Similar to Grok Bot and other tools that manage groups of AI agents, each project has "threads" running different tasks in parallel,
[3]
Anthropic launches Claude Code Projects, an 'always-on' conversation that remembers and delegates your long-running dev work
Anthropic today launched Claude Code Projects, a new way for developers using its hit "vibe coding" harness Claude Code to stay organized as they build something -- an app, website, or other development job -- that will require ongoing, persistent development work. The new Claude Code Projects is
Share
Copy Link
Anthropic introduced Claude Code Projects, an AI-powered coordination agent that manages multiple AI agents through persistent threads and shared memory. The feature helps developers handle long-running software development tasks but remains unavailable for local developers initially, with cloud sessions getting priority access for Claude Pro and Max subscribers.
Anthropic has launched Claude Code Projects, a redesigned feature that transforms how developers manage multiple AI agents during long-running software development tasks
1
3
. The AI-powered coordination agent introduces AI orchestration capabilities that allow Claude to scope requests, delegate work, coordinate parallel threads, review outputs, and assemble finished results1
. This addresses a pressing challenge in agentic workflows: keeping multiple coding agents synchronized and productive without constant manual intervention.
Source: VentureBeat
The feature operates as an always-on conversation that maintains context across development sessions. Anthropic describes the interaction model as briefing a chief-of-staff, where developers hand Claude several tasks at once while Claude decides whether each request belongs in a new or existing thread
3
. This shift matters because coding agents increasingly handle work extending beyond single prompts or pull requests, requiring persistent coordination layers that remember larger objectives.Claude Code Projects introduces persistent threads as addressable execution units, with each discussion becoming a full cloud session containing its own branch and repository copy
1
. These threads share memory across the project, allowing Claude to learn project details over time and apply them automatically to new work1
. This shared memory reduces the need for complex prompt engineering by preserving context that previously required developers to maintain external records and manually feed information back into new sessions3
.
Source: ZDNet
Developers gain mid-flight steering capabilities, allowing them to dig into running threads and redirect work without waiting for completion
1
. The architecture enables cross-repository collaboration, letting developers work across several repositories simultaneously with threads tied to each, then receive feedback on which pull requests need merging and in what order1
. An Overview panel surfaces items requiring user attention, while the coordinator routes new requests appropriately3
.The beta launch targets select Claude Pro and Max subscribers using cloud sessions in Claude Code who don't have existing projects on web and desktop platforms
1
2
. Existing Claude Pro and Max subscribers already using projects will have their current setups preserved, with upgrades coming later1
. Access will expand to Team and Enterprise users, along with Cowork and regular Claude chats2
.Local developers remain outside the new system for now, as threads currently run exclusively in the cloud
1
. Anthropic stated that support for running on local machines alongside local tools and code "is coming very soon"1
. The company emphasized this represents an additional feature without negative changes to local or CLI functionality1
. Cloud-based developers benefit from work continuing even after closing their laptops, with mobile check-ins planned for future releases1
.Related Stories
For enterprise systems, Claude Code Projects addresses the reality that business applications like digital storefronts, content management systems, and procurement platforms rarely have discrete endpoints
3
. These systems require continuous updates, patches, and adaptations over years, making persistent project memory valuable for maintaining context across ongoing development efforts3
.The feature joins similar tools like Grok Bot that manage groups of AI agents
2
. OpenAI, GitHub, and Google have all moved toward asynchronous workflows and longer-running agent capabilities3
. Anthropic's bet centers on developers needing not just another coding session, but a persistent coordination layer above several sessions that remembers larger objectives and routes work among them3
. The naming convention may cause confusion, as Anthropic already offers a separate Claude Projects feature introduced in June 2024 for general-purpose workspaces3
.Summarized by
Navi
[1]
09 Jan 2026•Technology

20 Oct 2025•Technology

29 Sept 2025•Technology

1
Science and Research

2
Technology

3
Technology
