惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
GbyAI
GbyAI
F
Fortinet All Blogs
Y
Y Combinator Blog
I
InfoQ
Microsoft Azure Blog
Microsoft Azure Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
Vercel News
Vercel News
T
The Blog of Author Tim Ferriss
P
Proofpoint News Feed
S
Schneier on Security
NISL@THU
NISL@THU
The Hacker News
The Hacker News
Simon Willison's Weblog
Simon Willison's Weblog
The GitHub Blog
The GitHub Blog
MyScale Blog
MyScale Blog
Cisco Talos Blog
Cisco Talos Blog
F
Full Disclosure
P
Palo Alto Networks Blog
T
The Exploit Database - CXSecurity.com
Know Your Adversary
Know Your Adversary
A
About on SuperTechFans
The Cloudflare Blog
T
Threat Research - Cisco Blogs
M
MIT News - Artificial intelligence
宝玉的分享
宝玉的分享
雷峰网
雷峰网
Hugging Face - Blog
Hugging Face - Blog
博客园 - 三生石上(FineUI控件)
D
DataBreaches.Net
Martin Fowler
Martin Fowler
H
Help Net Security
B
Blog RSS Feed
B
Blog
爱范儿
爱范儿
V
V2EX
I
Intezer
L
LangChain Blog
WordPress大学
WordPress大学
小众软件
小众软件
美团技术团队
Latest news
Latest news
H
Hackread – Cybersecurity News, Data Breaches, AI and More
T
Tor Project blog
L
Lohrmann on Cybersecurity
Cyberwarzone
Cyberwarzone
Last Week in AI
Last Week in AI
Project Zero
Project Zero
C
Cybersecurity and Infrastructure Security Agency CISA
V
Visual Studio Blog

Visual Studio Code - Code Editing. Redefined.

Visual Studio Code 1.130 (Insiders) Visual Studio Code 1.129 (Insiders) How Prompt Tuning Improved GPT-5.5 in VS Code Visual Studio Code 1.127 Visual Studio Code 1.128 Iterating faster with TypeScript 7 Visual Studio Code 1.126 What 50,000 Runs of a 5-Line Eval Taught Us Use your own language model key in VS Code Improving token efficiency for GitHub Copilot in VS Code December 2025 (version 1.108) November 2025 (version 1.107) October 2025 (version 1.106) September 2025 (version 1.105) August 2025 (version 1.104) July 2025 (version 1.103) June 2025 (version 1.102) May 2025 (version 1.101) April 2025 (version 1.100) March 2025 (version 1.99) Visual Studio Code 1.114 Visual Studio Code 1.116 Making agents practical for real-world development Visual Studio Code 1.111 How VS Code Builds with AI January 2026 (version 1.109) Visual Studio Code 1.113 Visual Studio Code 1.112 Visual Studio Code 1.115 Your Home for Multi-Agent Development Giving Agents a Visual Voice: MCP Apps Support in VS Code Building docfind: Fast Client-Side Search with Rust and WebAssembly Introducing the VS Code Insiders Podcast Introducing the Visual Studio Code Private Marketplace: Your Team's Secure, Curated Extension Hub 🎉 Open Source AI Editor: Second Milestone A Unified Experience for all Coding Agents Expanding Model Choice in VS Code with Bring Your Own Key Introducing auto model selection (preview) Command GitHub's Coding Agent from VS Code Open Source AI Editor: First Milestone The Complete MCP Experience: Full Specification Support in VS Code Beyond the tools, adding MCP in VS Code Context is all you need: Better AI results with custom instructions February 2026 (version 1.110) Enhance productivity with AI + Remote Dev Visual Studio Code 1.117 Visual Studio Code 1.118 Visual Studio Code 1.119 Visual Studio Code 1.120 The Coding Harness Behind GitHub Copilot in VS Code Visual Studio Code 1.122 Visual Studio Code 1.123 Building Long-Distance Next Edit Suggestions Visual Studio Code 1.125 Visual Studio Code 1.121 Visual Studio Code 1.124
VS Code: Open Source AI Editor
Microsoft · 2021-11-03 · via Visual Studio Code - Code Editing. Redefined.

Update (June 30th, 2025): the GitHub Copilot Chat extension is now open source.

May 19th, 2025 by the VS Code team

We believe that the future of code editors should be open and powered by AI. For the last decade, VS Code has been one of the most successful OSS projects on GitHub. We are grateful for our vibrant community of contributors and users who choose VS Code because it is open source. As AI becomes core to the developer experience in VS Code, we intend to stay true to our founding development principles: open, collaborative, and community-driven.

We will open source the code in the GitHub Copilot Chat extension under the MIT license, then carefully refactor the relevant components of the extension into VS Code core. This is the next and logical step for us in making VS Code an open source AI editor. It’s a reflection that AI-powered tools are core to how we write code; a reaffirmation of our belief that working in the open leads to a better product for our users and fosters a diverse ecosystem of extensions.

Why open source now?

Over the last few months, we’ve observed shifts in AI development that motivated us to transition our AI development in VS Code from closed to open source:

  • Large language models have significantly improved, mitigating the need for “secret sauce” prompting strategies.
  • The most popular and effective UX treatments for AI interactions are now common across editors. We want to enable the community to refine and build on these common UI elements by making them available in a stable, open codebase.
  • An ecosystem of open source AI tools and VS Code extensions has emerged. We want to make it easier for these extension authors to build, debug, and test their extensions. This is especially challenging today without access to the source code in the Copilot Chat extension.
  • We’ve gotten a lot of questions about the data that is collected by AI editors. Open sourcing the Copilot Chat extension enables you to see the data we collect, increasing transparency.
  • Malicious actors are increasingly targeting AI developer tools. Throughout VS Code’s history as OSS, community issues and PRs have helped us find and fix security issues quickly.

Next steps

In the coming weeks, we will work to open source the code in the GitHub Copilot Chat extension and refactor AI features from the extension into VS Code core. Our core priorities remain intact: delivering great performance, powerful extensibility, and an intuitive, beautiful user interface.

Open source works best when communities build around a stable, shared foundation. Thus, our goal is to make contributing AI features as simple as contributing to any part of VS Code. The stochastic nature of large language models makes it especially challenging to test AI features and prompt changes. To ease this, we will also make our prompt test infrastructure open source to ensure that community PRs can build and pass tests.

As usual, you can follow along on our iteration plan, where we will provide more information on this work. We will also keep our FAQ updated with answers to questions from the community. We welcome your feedback as we bring this vision to life.

We’re excited to shape the future of development as an open source AI editor - and we hope you’ll join us on this journey to build in the open.

Happy coding!

The VS Code team