Coding Tools
GitHub Copilot Projects and Computer Use go public
GitHub Changeloghigh confidence
Why it matters
- →Projects solve the fragmentation problem by keeping context across repos, Slack, and Figma in one persistent workspace.
- →Computer Use allows agents to interact with legacy desktop apps that lack APIs or MCP integrations.
- →The shift from ephemeral chat to persistent projects marks a move toward autonomous workflow orchestration.
GitHub has released public previews for two major features within its Copilot app: Projects and Computer Use. Projects provide a persistent workspace to coordinate work across multiple repositories, design tools like Figma, and communication platforms like Slack, allowing agents to manage complex, multi-step tasks rather than isolated code snippets. Simultaneously, the Computer Use feature enables Copilot to interact with desktop applications on macOS and Windows, performing actions such as clicking controls and entering text in apps lacking native APIs or MCP integrations. Both features require explicit user approval for actions and offer organizational controls to disable Computer Use if needed.
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 adds desktop computer use
GitHub Changelog · October 1, 2026 · Same story
- 2GitHub Copilot adds session continuity and computer use
GitHub Changelog · October 28, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot adds inline image generation
2 developments
- Oct 28 · GitHub Changelog
GitHub Copilot adds inline image generation - Oct 28 · GitHub Changelog
GitHub Copilot Projects and Computer Use go public (This article)↳ GitHub launches Projects for persistent multi-repo work and public Computer Use to control desktop apps directly.
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