GitHub Copilot sessions now support remote control across devices
GitHub has made remote control for Copilot sessions generally available on github.com and GitHub Mobile. The feature allows developers to start a coding session in VS Code or the command line and continue it from any device, including smartphones.
GitHub Copilot sessions now support remote control across devices
GitHub has released remote control functionality for GitHub Copilot sessions to general availability on github.com and GitHub Mobile.
The feature allows developers to start a coding session in VS Code or the command line interface and continue working from a different device, including mobile phones. This enables developers to switch between desktop and mobile environments without losing context in their active Copilot sessions.
Technical details
The remote control capability is now accessible through:
- github.com web interface
- GitHub Mobile applications
- VS Code desktop environment
- Command line interface
The feature has moved from preview or beta status to general availability, meaning it is now production-ready for all GitHub Copilot users.
Implementation
Developers can initiate a Copilot session on their local development environment and resume it from any authenticated device with access to GitHub. The system maintains session state across device transitions, allowing for continuity in code suggestions and context.
What this means
This release addresses a specific friction point in developer workflows: the inability to continue AI-assisted coding sessions when moving away from a primary workstation. While the practical utility of coding on a phone remains debatable for most serious development work, the feature provides flexibility for reviewing suggestions, making small edits, or continuing conversations with Copilot during commutes or when away from a desk. The move to general availability indicates GitHub has addressed stability and security concerns around remote session management.
Related Articles
AWS releases four multimodal evaluators for image-to-text AI tasks in Strands Evals SDK
AWS has added four multimodal evaluators to its Strands Evals SDK that judge image-to-text AI outputs by directly analyzing source images. The evaluators—Overall Quality, Correctness, Faithfulness, and Instruction Following—use multimodal large language models to detect visual hallucinations, factual errors, and instruction violations that text-only judges miss.
AWS SageMaker AI adds bidirectional streaming for real-time speech transcription with vLLM
Amazon SageMaker AI has launched bidirectional streaming support for real-time inference, enabling WebSocket-based voice applications through vLLM integration. The feature uses HTTP/2 on port 8443 to bridge client connections with vLLM's Realtime API, allowing audio to stream in while transcription streams back simultaneously over a single persistent connection.
Google launches Universal Cart, an AI agent that shops across multiple retailers in one checkout
Google announced Universal Cart at its I/O developer conference, an AI-powered shopping system that consolidates purchases from multiple retailers including Target, Shopify, Wayfair, and Etsy into a single checkout. The feature uses Gemini's agentic AI to verify product compatibility, suggest better deals, and automate routine purchases.
Google Announces Gemini Spark Agent and Antigravity Platform at I/O, Launch Date Not Disclosed
Google announced Gemini Spark at I/O 2026, positioning it as a competitor to OpenAI's Claude-based agents. The service will integrate with Gmail, Calendar, Drive, and other Google apps, running on Gemini 3.5 Flash and a new platform called Antigravity. No general availability date has been disclosed.
Comments
Loading...