Coding Tools
GitHub Copilot Sandboxes Enter Public Preview
GitHub Changeloghigh confidence
Why it matters
- →Provides a secure environment for executing agent-generated code, enhancing security for developers.
- →Standardizes isolation across multiple operating systems, ensuring consistent user experience.
- →Supports enterprise policy enforcement, allowing centralized control over Copilot's execution.
GitHub has announced the public preview of secure, isolated sandboxes for its Copilot tool, available both locally and in the cloud. These sandboxes allow Copilot to execute commands and interact with code in a controlled environment, enhancing security and control for developers. Built on Microsoft MXC technology, the sandboxes offer a consistent experience across different operating systems. This development marks a shift in Copilot's role from an in-editor assistant to a more autonomous coding partner, capable of executing tasks while maintaining strict security protocols.
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.
What happened next
- 1GitHub Copilot App Now Generally Available
GitHub Changelog · June 17, 2026 · Same story
- 2GitHub Copilot adds local sandboxing
GitHub Changelog · September 23, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot Sandboxes Enter Public Preview
5 developments
- Jun 2 · GitHub Changelog
GitHub Copilot Sandboxes Enter Public Preview (This article) - Jun 2 · GitHub Changelog
GitHub Copilot CLI Gets Major Refresh↳ GitHub Copilot CLI adds terminal tabs, a rubber duck agent, voice input, and prompt scheduling. - Jun 2 · GitHub Changelog
GitHub Copilot SDK Now Generally Available↳ GitHub Copilot SDK is now generally available with stable API access for agentic engine integration and multi-turn sessions. - Jun 5 · Matt Wolfe
GitHub Releases Copilot App for Desktop - Jun 10 · Matt Wolfe
GitHub Copilot App Now Supports Any Model Provider↳ The desktop app now supports any AI model provider.
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.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
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.
llama.cpp Releases