Coding Tools
GitHub Copilot Memory Enhances Control Features
GitHub Changeloghigh confidence
Why it matters
- →Provides users with more control over memory management in GitHub Copilot.
- →Enhances privacy and customization for repository admins and users.
- →Simplifies memory management through the Copilot CLI.
GitHub has updated its Copilot Memory feature, enhancing user control over memory management. The update introduces a repository-level off switch, allowing admins to disable memory storage for specific repositories. Additionally, the Copilot CLI now supports commands to manage memory settings, providing users with straightforward options to enable, disable, or check memory status. These changes are part of GitHub's ongoing efforts to refine Copilot Memory, currently in public preview for all paid Copilot plans.
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.
How we got here
- 1GitHub Copilot Memory Adds User Preferences
GitHub Changelog · May 15, 2026 · Same story
What happened next
- 2GitHub Copilot for JetBrains Enhances Features
GitHub Changelog · August 11, 2026 · Same story
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.