Coding Tools
Claude Code relaunches Projects for multi-agent coordination
The Verge AIhigh confidence
Why it matters
- →Enables parallel execution of AI coding tasks across multiple repository branches.
- →Introduces a coordinator agent model for managing complex, multi-step development workflows.
- →Shifts Claude Code from single-session chat to a structured project management environment.
Anthropic has relaunched the Projects feature within Claude Code, enabling users to manage multiple AI agents working in parallel cloud sessions. Each thread operates on its own repository branch, coordinated by a central agent that distributes tasks and maintains shared memory. The system supports subagents, loops, and workflows to handle complex assignments, with manual resolution required for code merge conflicts. Initially available in beta for select Pro and Max subscribers, the feature will expand to Team and Enterprise users later.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More from The Verge AI
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
