
GitHub has launched Agent Plugins 1.0, an open standard that allows developers to create a single plugin for use across multiple agent clients like VS Code and GitHub Copilot. This initiative, supported by companies such as AWS, Microsoft, and Google, aims to reduce duplication in plugin development by standardizing the packaging of agent skills and MCP servers. The new system is designed to streamline the process for developers, enabling them to manage and distribute plugins more efficiently. Existing plugins remain supported, ensuring a smooth transition for current users.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
WIRED AI · May 26, 2026 · Background
TechCrunch AI · June 2, 2026 · Related
GitHub Changelog · June 3, 2026 · Related
Cole Medin · June 11, 2026 · Background
GitHub Changelog · August 31, 2026 · Same story
OpenAI · September 10, 2026 · Background
Sam Witteveen · September 14, 2026 · Related
The Verge AI · September 25, 2026 · Related
Claude Code Releases · October 6, 2026 · Related
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.
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.
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.