Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 4 месяцев назад •via X (Twitter)

Комментарии: 42

Фото профиля Pierce Boggan
Pierce Boggan4 месяцев назад

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.

Фото профиля Pierce Boggan
Pierce Boggan4 месяцев назад

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:

Фото профиля Pierce Boggan
Pierce Boggan4 месяцев назад

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.

Фото профиля Pierce Boggan
Pierce Boggan4 месяцев назад

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

Фото профиля Stephen Turner 🇬🇧🇺🇦
Stephen Turner 🇬🇧🇺🇦4 месяцев назад

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

Фото профиля Abram Jackson
Abram Jackson4 месяцев назад

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?

Фото профиля Pierce Boggan
Pierce Boggan4 месяцев назад

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

Фото профиля lioncubs
lioncubs3 месяцев назад

@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” 😭

Фото профиля Pierce Boggan
Pierce Boggan3 месяцев назад

@burkeholland Adding @BrigitMurtaugh for Agents app + remote development

Фото профиля Jun(e)
Jun(e)4 месяцев назад

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

Фото профиля Prismor
Prismor4 месяцев назад

We love VS code! Thanks for shipping this

Фото профиля AI Inc
AI Inc4 месяцев назад

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

Фото профиля CapyToolkit
CapyToolkit4 месяцев назад

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

Фото профиля Nilay
Nilay4 месяцев назад

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?

Фото профиля Ami Schreiber
Ami Schreiber4 месяцев назад

It’s the ADHD window!

Фото профиля tianma
tianma4 месяцев назад

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

Фото профиля lifcc
lifcc4 месяцев назад

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.

Фото профиля armandoki
armandoki4 месяцев назад

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

Фото профиля Pierce Boggan
Pierce Boggan4 месяцев назад

What do you think?

Фото профиля armandoki
armandoki3 месяцев назад

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

Фото профиля Abdi Daud
Abdi Daud4 месяцев назад

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

Фото профиля David Dossett
David Dossett3 месяцев назад

congrats on the 🚢!

Фото профиля Eshetie ፼ Liku
Eshetie ፼ Liku4 месяцев назад

#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.

Фото профиля Sant
Sant4 месяцев назад

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

Фото профиля Daniel
Daniel4 месяцев назад

Too bad no one can afford to do that now.

Фото профиля spencer
spencer3 месяцев назад

wicked

Фото профиля Niclas
Niclas4 месяцев назад

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

Фото профиля Aravind Putrevu
Aravind Putrevu3 месяцев назад

This looks like superset!

Фото профиля RAFA™
RAFA™3 месяцев назад

@sseraphini 👏🏽👏🏽

Фото профиля Egor Egorov
Egor Egorov3 месяцев назад

@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.

Фото профиля Pierce Boggan
Pierce Boggan3 месяцев назад

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

Фото профиля Egor Egorov
Egor Egorov3 месяцев назад

@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!

Фото профиля Filip Mares
Filip Mares3 месяцев назад

It's my daily. Love it!

Фото профиля Prompt Heat
Prompt Heat3 месяцев назад

WTF? i cant buy other plans , this is bullshit

Фото профиля Alexander Rehm
Alexander Rehm3 месяцев назад

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

Фото профиля Iulian Lita
Iulian Lita3 месяцев назад

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.

Фото профиля Tanay Salpekar
Tanay Salpekar3 месяцев назад

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

Фото профиля Tech With Matteo
Tech With Matteo4 месяцев назад

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

Фото профиля Rennan Felizardo
Rennan Felizardo4 месяцев назад

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

Фото профиля Sergio Pereira
Sergio Pereira3 месяцев назад

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

Фото профиля Anthony Humphreys
Anthony Humphreys4 месяцев назад

@JamesMontemagno Need more sidebars @pierceboggan !

Фото профиля Gaurang Karia
Gaurang Karia3 месяцев назад

Looks great.. looking forward to using it.

Похожие видео

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 просмотров • 1 год назад