Take your local GitHub sessions anywhere

2026-05-18 · Source: The GitHub Blog · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning · Depth: Intermediate, short

Summary

GitHub has made remote control for GitHub Copilot CLI sessions generally available as of May 18, 2026, extending its functionality to github.com and the GitHub Mobile app. This feature also introduces remote control capabilities within VS Code and JetBrains IDEs, enabling a truly multi-surface experience across devices. Developers can initiate a Copilot session in VS Code or the CLI, then use the "/remote on" command to monitor progress and interact with it from their web browser or mobile device. This allows for real-time tracking of Copilot's actions, sending additional natural language instructions to redirect or expand scope, and completing full development workflows, including reviewing and merging pull requests, all while away from their primary workstation. Sessions remain private by default, visible only to the user.

Key takeaway

For software engineers managing multiple GitHub Copilot agent sessions or needing development flexibility, you can now maintain continuous control from any device. This new remote control feature allows you to monitor, steer, and complete entire workflows, including pull request management, directly from github.com or the GitHub Mobile app. Update your GitHub Copilot CLI and GitHub Mobile app to seamlessly transition your coding sessions from desktop to on-the-go, ensuring your productivity isn't tied to your desk.

Key insights

GitHub Copilot's remote control enables continuous, multi-surface AI-assisted development workflows across devices.

Principles

• Agentic AI extends developer workflows beyond the desktop.
• Remote development sessions maintain user privacy by default.

Method

Initiate a Copilot session in VS Code or CLI, then use "/remote on" to access and manage it from github.com or the GitHub Mobile app.

In practice

• Monitor Copilot's real-time progress and file changes remotely.
• Send natural language instructions to steer or expand agent scope.
• Complete pull request review and merge directly from mobile.

Topics

• GitHub Copilot
• Remote Control
• Developer Workflow
• GitHub Mobile
• VS Code
• Agentic AI

Code references

• microsoft/copilot-intellij-feedback
• site/privacy

Best for: NLP Engineer, Software Engineer, AI Engineer, Machine Learning Engineer

Related on AIssential

• GitHub recognized as a Leader in the Gartner® Magic Quadrant™ for Enterprise AI Coding Agents for the third year in a row — AI coding agents are shifting software development from code generation to orchestrating outcomes across the entire SDLC.
• GitHub Copilot Adds Persistent Memory for Repository-Level Context — GitHub Copilot's new persistent memory retains repository-level context, improving long-term coding assistance and code review.
• OpenAI says Codex is coming to your phone — OpenAI's Codex now offers mobile and desktop control, intensifying competition in agentic coding tools.
• GitHub Slashes Agent Workflow Token Spend up to 62% with Daily Audits and MCP Pruning — GitHub cut LLM agent token spend up to 62% via daily audits, MCP pruning, and GitHub CLI integration.
• Changes to GitHub Copilot Individual plans — Agentic AI workflows significantly increase compute demands, necessitating pricing model adjustments.
• Microsoft caught sneaking "Co-Authored-by Copilot" into VS Code commits - even with AI off — Undisclosed AI attribution in code commits can lead to significant user distrust and policy conflicts.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The GitHub Blog.