Visual Studio Code documentation

Get started with AI agents

Hand off tasks to autonomous AI agents that iterate until the job is done. Run them locally, in the background, or in the cloud, with your choice of AI provider. Track all sessions without leaving VS Code.

Get started →

What do you want to do?

Optimize your AI usage

Tips to help you get the most out of AI agents, while optimizing for cost and performance.

Test and debug with browser agents

Let AI agents use the integrated browser to validate and fix issues in your application.

Customize AI for your project

Configure custom instructions, skills, and MCP servers to tailor AI to your workflow.

Set up VS Code

Install VS Code on Windows, macOS, or Linux and get running.

Learn VS Code basics

Explore the editor, settings, extensions, and key features.

VS Code for enterprise

Learn how to configure VS Code for enterprise environments with policies, extension management, and AI customization options.

Latest

release

VS Code 1.126 release

Session-level cost transparency, a unified model customization picker, and Restricted Mode for new folders.

documentation

Approvals and permissions

Configure agent approvals and permissions to work efficiently but safely.

blog

What 50,000 runs of a 5-line eval taught us

How AI coding models calibrate effort, token cost, and tool use on even the simplest task, and what that means for model selection.