Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

VS Code was already used by millions of developers for agentic coding. However, the editor layout has traditionally been optimized for single-task and single-workspace workflows. Today, we're introducing a new window to enable our users (and ourselves!) to work with multiple agents across multiple projects: Agents. Now available in...

151,517 görüntüleme • 4 ay önce •via X (Twitter)

42 Yorum

Pierce Boggan profil fotoğrafı
Pierce Boggan4 ay önce

Agents window reflects how our own workflows on the VS Code team evolved to focus more on higher-level partnership with the agent. A year ago, many of us used to spend an immense amount of time following the specific agent trajectory, including the tool calls and edits it made. Now, we spend our time building alignment with the models with features like Plan mode, and reviewing outcomes as a first step rather than code.

Pierce Boggan profil fotoğrafı
Pierce Boggan4 ay önce

The Agents window also expands our vision with Agent HQ to not just give you choice in state of the art models, but also harnesses as well. Give our Claude agent integration a try, all powered by your GitHub Copilot subscription:

Pierce Boggan profil fotoğrafı
Pierce Boggan4 ay önce

We also want to be able to continue our work from anywhere. The Agents window also includes support for remote development, allowing you to connect to coding agents running in remote hosts, such as a cloud sandbox.

Pierce Boggan profil fotoğrafı
Pierce Boggan4 ay önce

We also built a brand new experience to allow you to work from the browser (including mobile!) with your coding agents!

Stephen Turner 🇬🇧🇺🇦 profil fotoğrafı
Stephen Turner 🇬🇧🇺🇦4 ay önce

I look forward to the Codex harness being included. This is the way.

Abram Jackson profil fotoğrafı
Abram Jackson4 ay önce

Terrific! Do you use the words "Agents" and "sessions" interchangeably? Or is an "agent" a combination of repo with its skills and enabled MCP Servers?

Pierce Boggan profil fotoğrafı
Pierce Boggan4 ay önce

Nope, though sometimes I accidentally do :D Agent = core agent loop = the prompt, tools, context. In VS Code, we support multiple agent types, including VS Code (Local), Copilot CLI, Claude Session = An instance of that agent in a particular repo/workspace

lioncubs profil fotoğrafı
lioncubs3 ay önce

@burkeholland @pierceboggan this app shows NO Love to the ultimate Remote Session WSL - what about sessions in devcontainers as well??? Also another awesome “Remote Session” 😭

Pierce Boggan profil fotoğrafı
Pierce Boggan3 ay önce

@burkeholland Adding @BrigitMurtaugh for Agents app + remote development

Jun(e) profil fotoğrafı
Jun(e)4 ay önce

any plan to support TUI ? actually I mean the support for opencode / codex / claude code

Prismor profil fotoğrafı
Prismor4 ay önce

We love VS code! Thanks for shipping this

AI Inc profil fotoğrafı
AI Inc4 ay önce

Nice feature, but I cancelled my GitHub Copilot Pro+ account now, because of the high prices coming up... Good luck!

CapyToolkit profil fotoğrafı
CapyToolkit4 ay önce

Thanks for shipping this @pierceboggan! VS Code rocks 🤘🏻

Nilay profil fotoğrafı
Nilay4 ay önce

Hey quick question, is there information to access, why suddenly my locally hosted models and BYOMs (from Foundry etc.) are no longer visible and accessible via VS Code Chat or Agents? Is there a shift?

Ami Schreiber profil fotoğrafı
Ami Schreiber4 ay önce

It’s the ADHD window!

tianma profil fotoğrafı
tianma4 ay önce

只能使用copilot的模型,我不会去用,我使用codex,claude价格公道。

lifcc profil fotoğrafı
lifcc4 ay önce

Agents window is the right primitive. The pain is not launching another agent; it is keeping repo state, diffs, terminal output, and handoff visible when two projects are moving at once.

armandoki profil fotoğrafı
armandoki4 ay önce

I’ve been using it a lot the past few weeks. 😎

Pierce Boggan profil fotoğrafı
Pierce Boggan4 ay önce

What do you think?

armandoki profil fotoğrafı
armandoki3 ay önce

I'm so glad we're building this! Lots of thoughts. Will ping you.

Abdi Daud profil fotoğrafı
Abdi Daud4 ay önce

Well done team; I've been using it for sometime glad to see it in stable. Do you have a plan for scheduled tasks say that run on cloud and/or PC

David Dossett profil fotoğrafı
David Dossett3 ay önce

congrats on the 🚢!

Eshetie ፼ Liku profil fotoğrafı
Eshetie ፼ Liku4 ay önce

#coolstorybro I ran out of premium requests from my copilot pro+ subscription in the first week, all(most?) requests are user initiated. The allotment does not match the IDE/AI work @code is making. Difficult position to be in for me.

Sant profil fotoğrafı
Sant4 ay önce

love visual studio code for agentic development much better that anything else out there. but multiple agents across multiple projects... sounds like software apocalypse.

Daniel profil fotoğrafı
Daniel4 ay önce

Too bad no one can afford to do that now.

spencer profil fotoğrafı
spencer3 ay önce

wicked

Niclas profil fotoğrafı
Niclas4 ay önce

Remote SSH sessions will not work/break for me ...

Aravind Putrevu profil fotoğrafı
Aravind Putrevu3 ay önce

This looks like superset!

RAFA™ profil fotoğrafı
RAFA™3 ay önce

@sseraphini 👏🏽👏🏽

Egor Egorov profil fotoğrafı
Egor Egorov3 ay önce

@film_girl Is actual programming still supported? I use vscode since Atom inception. It would be kind of sad to update one day and see code editor gone.

Pierce Boggan profil fotoğrafı
Pierce Boggan3 ay önce

@film_girl 💯, editor isn't going anywhere! We are landing improvements to that experience too. New markdown experience just shipped yesterday!

Egor Egorov profil fotoğrafı
Egor Egorov3 ay önce

@film_girl Oh yes, I was pleasantly surprised with that yesterday! These days it was unexpected. It is actually what I was missing from vs code and thus it is a very welcome addition!

Filip Mares profil fotoğrafı
Filip Mares3 ay önce

It's my daily. Love it!

Prompt Heat profil fotoğrafı
Prompt Heat3 ay önce

WTF? i cant buy other plans , this is bullshit

Alexander Rehm profil fotoğrafı
Alexander Rehm3 ay önce

Odd bug, with @claudeai windows I'm only ever seeing Haiku as the model, despite the existing sessions being Sonnet or Opus. Known issue?

Iulian Lita profil fotoğrafı
Iulian Lita3 ay önce

Doesn't really matter. The upcoming copilot changes make all this kinda useless. Let's wait a few months to see what will change after 20-30%+ of the users will cancel their copilot sub.

Tanay Salpekar profil fotoğrafı
Tanay Salpekar3 ay önce

The app looks / feels great. The only thing: I’m not trying to pay API usage rates with 3rd party models.

Tech With Matteo profil fotoğrafı
Tech With Matteo4 ay önce

running multiple agents across projects at once is exactly where the real productivity gains are, the single-task editor felt like a bottleneck once you get used to parallel work

Rennan Felizardo profil fotoğrafı
Rennan Felizardo4 ay önce

it's indeed a good app, but unfortunately I stopped using it at the company months ago due to the lack of GHE cloud support. Session delegation to copilot cli doesn't work when the host is not the default one. Which is quite odd since GitHub and VS Code are backed by Microsoft

Sergio Pereira profil fotoğrafı
Sergio Pereira3 ay önce

Have you been able to manage what happens when two of those agents edit the same file? Worktrees isn't the solution....

Anthony Humphreys profil fotoğrafı
Anthony Humphreys4 ay önce

@JamesMontemagno Need more sidebars @pierceboggan !

Gaurang Karia profil fotoğrafı
Gaurang Karia3 ay önce

Looks great.. looking forward to using it.

Benzer Videolar

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 görüntüleme • 1 yıl önce