Coding Tools
JetBrains IDEs Preview Claude as Agent Provider
GitHub Changeloghigh confidence
Why it matters
- →The integration of Claude as an agent provider offers developers more flexibility in choosing AI tools.
- →Custom agents at the organization and enterprise levels streamline workflow standardization.
- →Enhanced model picker and AI credit visibility improve user experience and control.
JetBrains IDEs have rolled out a public preview of Claude as an agent provider within GitHub Copilot, offering developers more flexibility in agent selection. This update supports custom agents at the organization and enterprise levels, allowing for standardized workflows across teams. The Claude integration, while still in bypass permissions mode, adds a new layer of choice for users. Enhancements to the model picker and AI credit indicators further improve the user experience, making AI-driven development more intuitive and efficient.
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 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.