← 返回首页
Cloud agents in Visual Studio Code

Documentation

Topics Overview Overview Linux macOS Windows VS Code for the Web Raspberry Pi Network Additional Components Uninstall VS Code Tutorial Copilot Quickstart User Interface Personalize VS Code Install Extensions Tips and Tricks Intro Videos Overview Setup Quickstart Overview Language Models Context Tools Agents Customization Trust & Safety Overview Agents Tutorial Agents Window Planning Memory Tools Subagents Local Agents Copilot CLI Cloud Agents Third-Party Agents Overview Chat Sessions Add Context Inline Chat Review Edits Checkpoints Artifacts Panel Debug Chat Interactions Prompt Examples Overview Instructions Prompt Files Custom Agents Agent Skills Language Models MCP Hooks Plugins Context Engineering Customize AI Test-Driven Development Edit Notebooks with AI Test with AI Test Web Apps with Browser Tools Debug with AI MCP Dev Guide OpenTelemetry Monitoring Inline Suggestions Smart Actions Best Practices Security Troubleshooting FAQ Cheat Sheet Settings Reference MCP Configuration Workspace Context Display Language Layout Keyboard Shortcuts Settings Settings Sync Extension Marketplace Extension Runtime Security Themes Profiles Overview Voice Interactions Command Line Interface Telemetry Basic Editing IntelliSense Code Navigation Refactoring Snippets Overview Multi-Root Workspaces Workspace Trust Tasks Debugging Debug Configuration Testing Port Forwarding Integrated Browser Overview Quickstart Staging & Committing Branches & Worktrees Repositories & Remotes Merge Conflicts Collaborate on GitHub Troubleshooting FAQ Getting Started Tutorial Terminal Basics Terminal Profiles Shell Integration Appearance Advanced Overview Enterprise Policies AI Settings Extensions Telemetry Updates Overview JavaScript JSON HTML Emmet CSS, SCSS and Less TypeScript Markdown PowerShell C++ Java PHP Python Julia R Ruby Rust Go T-SQL C# .NET Swift Working with JavaScript Node.js Tutorial Node.js Debugging Deploy Node.js Apps Browser Debugging Angular Tutorial React Tutorial Vue Tutorial Debugging Recipes Performance Profiling Extensions Tutorial Transpiling Editing Refactoring Debugging Quick Start Tutorial Run Python Code Editing Linting Formatting Debugging Environments Testing Python Interactive Django Tutorial FastAPI Tutorial Flask Tutorial Create Containers Deploy Python Apps Python in the Web Settings Reference Getting Started Navigate and Edit Refactoring Formatting and Linting Project Management Build Tools Run and Debug Testing Spring Boot Modernizing Java Apps Application Servers Deploy Java Apps GUI Applications Extensions FAQ Intro Videos GCC on Linux GCC on Windows GCC on Windows Subsystem for Linux Clang on macOS Microsoft C++ on Windows Build with CMake CMake Tools on Linux CMake Quick Start C++ Dev Tools for Copilot Editing and Navigating Debugging Configure Debugging Refactoring Settings Reference Configure IntelliSense Configure IntelliSense for Cross-Compiling FAQ Intro Videos Get Started Navigate and Edit IntelliCode Refactoring Formatting and Linting Project Management Build Tools Package Management Run and Debug Testing FAQ Overview Node.js Python ASP.NET Core Debug Docker Compose Registries Deploy to Azure Choose a Dev Environment Customize Develop with Kubernetes Tips and Tricks Overview Jupyter Notebooks Data Science Tutorial Python Interactive Data Wrangler Quick Start Data Wrangler PyTorch Support Azure Machine Learning Manage Jupyter Kernels Jupyter Notebooks on the Web Data Science in Microsoft Fabric Foundry Toolkit Overview Foundry Toolkit Copilot Tools Create Agents Models Playground Agent Builder Agent Inspector Evaluation Tool Catalog Fine-Tuning (Automated Setup) Fine-Tuning (Project Template) Model Conversion Tracing Profiling (Windows ML) FAQ File Structure Manual Model Conversion Manual Model Conversion on GPU Setup Environment Without Foundry Toolkit Template Project Migrating from Visualizer to Agent Inspector Overview Getting Started Resources View Deployment VS Code for the Web - Azure Containers Azure Kubernetes Service Kubernetes MongoDB Remote Debugging for Node.js Overview SSH Dev Containers Windows Subsystem for Linux GitHub Codespaces VS Code Server Tunnels SSH Tutorial WSL Tutorial Tips and Tricks FAQ Overview Tutorial Attach to Container Create Dev Container Advanced Containers devcontainer.json Dev Container CLI Tips and Tricks FAQ Default Keyboard Shortcuts Default Settings Substitution Variables Tasks Schema
Copy as Markdown

On this page there are 4 sections

Try this

Cloud agents in Visual Studio Code

Cloud agents run on remote infrastructure and integrate with GitHub repositories for team collaboration through pull requests. For example, the GitHub Copilot cloud agent runs on GitHub's infrastructure and can implement features, address code review feedback, and open pull requests autonomously.

This article covers the key features of cloud agents, and how to start and manage cloud agent sessions for coding tasks that can range anywhere from simple to complex.

What are cloud agents?

Unlike local and background agents that run on your local machine, cloud agents like Copilot cloud agent run on remote infrastructure. You can view and manage all your cloud agent sessions from the unified Chat view in VS Code. This view also lets you create new cloud agent sessions directly from VS Code or hand off local or background agent conversations to cloud agents.

VS Code supports different cloud agents, such as Copilot cloud agent and third-party agents like Claude and Codex.

Tip

If you prefer an agent-first surface for running cloud agent sessions alongside Copilot CLI and Claude sessions across multiple projects, use the Agents window. Sessions are shared between the main VS Code window and the Agents window.

Because cloud agents run remotely without user interaction, they are well-suited for tasks that have a well-defined scope and all necessary context. Their integration with pull requests makes them very effective for team collaboration.

Due to their remote execution environment, cloud agents can't directly access VS Code built-in tools and run-time context (like failed tests or text selections). They are limited to the MCP servers and language models that are configured in the cloud agent service.

To assign a task to a cloud agent, you can either create a new cloud session directly from the Chat view or hand off a local or background agent conversation from VS Code to a cloud agent.

GitHub Copilot cloud agent

The GitHub Copilot cloud agent is the primary cloud agent available in VS Code with your Copilot subscription.

Key capabilities include:

  • Large-scale refactoring across your GitHub repository
  • Complete feature implementation from high-level requirements
  • Automatic pull request generation with detailed descriptions
  • Code review integration and feedback addressing

Third-party cloud agents

VS Code supports third-party cloud agents like Claude coding agent and Codex coding agent as options for cloud agent sessions. You need to enable support for third-party agents in the cloud in your Copilot account settings before you can use them in VS Code.

You don't need to install the provider's VS Code extension to use their cloud agent in VS Code.

Learn more about third-party agents in VS Code and how to enable them.

Start a cloud agent session

You can start a cloud agent session either directly by sending a chat prompt to a cloud agent or by handing off an ongoing local or background conversation to a cloud agent. Handing off an ongoing conversation is especially useful for complex tasks that require initial clarification or planning before autonomous execution.

If you prefer to work in the browser, you can also start cloud agent sessions directly from GitHub.com using the GitHub Copilot cloud agent.

Create a new cloud agent session

To create a new cloud agent session:

  1. In the Chat view, select New Chat from the session list dropdown and choose Cloud from the session type dropdown

    Alternatively, you can run the Chat: New Cloud Agent command from the Command Palette (⇧⌘P (Windows, Linux Ctrl+Shift+P)).

  2. Choose the cloud agent provider from the dropdown and optionally select a custom agent and model.

  3. Enter your prompt and let the cloud agent work on the task

    For example, you might enter: