ToolsSeptember 17, 2026via The Verge AI
Claude Code relaunches Projects to manage multiple AI agents in the cloud
Why it matters
Anthropic is shipping agent management infrastructure directly into Claude Code—shared memory, parallel task execution, and conflict resolution. This moves agent coordination from external frameworks into the product itself, changing how teams deploy and scale multi-agent workflows.
Key signals
- Claude Code Projects enables multiple agents to run in parallel under one coordinator
- Shared memory, goals, and artifact library across agents
- Each thread runs as independent Claude Code cloud session on separate repo branch
- Merge-conflict resolution when threads work on overlapping code
- Threads can further delegate and split work (hierarchical task decomposition)
- Architecture mirrors multi-agent orchestration tools like Grok Bot
- Cloud-native deployment model
The hook
Claude Code just turned multi-agent orchestration into a native feature. Practitioners managing agent teams in production should pay attention.
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, …