Loading video...

Video Failed to Load

Go Home

Granular code control or prompt-driven development? In Antigravity, you exist in both worlds. Dive into the Editor for deep work. Pull back to the Agent Manager to manage multiple agents across workspaces. Switch between them instantly. Watch the Manager and Editor in sync 👇

70,431 views • 10 months ago •via X (Twitter)

34 Comments

Swapan Kumar Manna's profile picture
Swapan Kumar Manna10 months ago

just been living in Antigravity for the past 3 weeks and honestly, i’m obsessed. the way I can stay deep in the Editor with multi-agent stuff flying around, then instantly flip to writing real code or tweaking tools without breaking flow is insane. Agent Manager makes juggling workspaces feel effortless. it never makes me choose between “go fast with prompts” and “stay precise with code” — it just gives me both, exactly when i need them. first tool that actually feels built for how i think.

Morrison⚡️ 🇨🇦's profile picture
Morrison⚡️ 🇨🇦10 months ago

Getting a lot of these types of errors lately on your free compute. I guess the app needs a bit of work or you are just deprioritizing the free users?

Beralyne Alex's profile picture
Beralyne Alex10 months ago

Hello, Antigravity's best lover here. I have been experiencing this error all day. What might be the issue?

Mehmet's profile picture
Mehmet10 months ago

Gemini 3 is not the way you first showed it to us. Please review the restrictions you have applied

Hop's profile picture
Hop10 months ago

Have you increased the limits? I've wasted enough time trying Antigravity only to run into limit issues and not have anything to show for the time and effort. Is Google dogfooding Antigravity?

Justin C. Gohn's profile picture
Justin C. Gohn10 months ago

Is this tool worth my time right now? Have heard lots of complaints on the timeline

Certified AI Dev's profile picture
Certified AI Dev10 months ago

Considering this is the worst version it’s ever going to be, I am pretty impressed with how Antigravity compares with other IDEs. More info below: 👇🏻

Samael Garcia's profile picture
Samael Garcia10 months ago

Do you have in mind to add Claude Opus 4.5 and Claude Opus 4.5 thinking ? it could be a strong implementation .

Zan's profile picture
Zan10 months ago

Fix the agent loading issue - the window is in always loading state. I've already sent the report. Tried logging out and reinstalling. It happened on Mac.

Deependra Solanky's profile picture
Deependra Solanky10 months ago

Single window > Multi-window. Cursor: Seamless toggle between Editor and Agent modes in one window. ✅ Antigravity: Opens two windows for every project (Agent + Editor). ❌ The double window setup feels like unnecessary clutter. Keep it unified!

Arvind Prajapati's profile picture
Arvind Prajapati10 months ago

World want a speech conversation feature where we can prompt and get reply both in speech not by writing and in background gemini does the coding

Dharma's profile picture
Dharma10 months ago

I’m curious how the Editor and Manager stay perfectly in sync while juggling multiple agents!!!

Snow Protocol's profile picture
Snow Protocol10 months ago

I was able to fix a navigation bug with the help of Antigravity today

Ben's profile picture
Ben10 months ago

I said I’d give this a week of full use to see if I could switch and I might be convinced.

Matt Jasper's profile picture
Matt Jasper10 months ago

I just need more time before limits kick in please

Max Calkin's profile picture
Max Calkin10 months ago

Just a little slow during peak hours and deep agentic flow. Loving it so much all around! Good job @antigravity team!

Gorden Wuebbe's profile picture
Gorden Wuebbe10 months ago

your product rocks. i would love to be a heavy user, but fter 1-3 babysteps, i got usage limits..

Farseen's profile picture
Farseen10 months ago

make it usable on intel mac

Ananya Patelik's profile picture
Ananya Patelik10 months ago

I'll be in the editor for deep debugging when a pipeline fails at 2am. But using the agent to scaffold the boilerplate for a new ingestion pipeline? That's compelling. The switch needs to be seamless.

André Hugo's profile picture
André Hugo10 months ago

The agent is too slow

Jonny D's profile picture
Jonny D10 months ago

Excited for continued updates. Cursor and Antigravity, what a world man

Chinmay 💻🍡🧩's profile picture
Chinmay 💻🍡🧩10 months ago

Response latency is way too high

manthoR's profile picture
manthoR10 months ago

Figma mcp broken ?

Arveni's profile picture
Arveni10 months ago

Antigravity still feels like magic to me. Great work! Will definitely keep using it!

Ajitesh Shukla's profile picture
Ajitesh Shukla10 months ago

Great product, team! Am using it and loving it. Focus has now turned to value creation!

omer khan's profile picture
omer khan10 months ago

what is this issue?

Agyeya's profile picture
Agyeya10 months ago

Your agentic IDE is saving my solo grind—parallel agents = fake team vibes.

wsi's profile picture
wsi10 months ago

how to be sure the code is correct while some agents are making changes to the same code?

Karan Jagtiani's profile picture
Karan Jagtiani10 months ago

The dual setup really does help maintain focus. Curious how the sync handles larger projects-any hiccups there?

Pratap's profile picture
Pratap10 months ago

The eternal developer dilemma: 'Did this code come from my brain or the AI?' The answer is yes. At this point, the best code wins regardless of its origin story. Both worlds colliding means infinite possibilities and infinite ways to debug them.

Mr Z's profile picture
Mr Z10 months ago

Based

Yùuuuuuuuuuuu's profile picture
Yùuuuuuuuuuuu10 months ago

Too many 429.

⚡️ nedzen.eth's profile picture
⚡️ nedzen.eth10 months ago

this is amazing, a great tool ! bravo google when can I pay for it? I'm ready to replace cursor.

Note Command .com (try it out!)'s profile picture
Note Command .com (try it out!)10 months ago

I heard about a guy where you removed their D:/ drive. What do you make of that?

Related Videos

Agents 2.0 is here. Anthropic. OpenAI. xAI. Are all racing to build your next AI coworker. Agents that can work alongside humans, talk to other agents, and coordinate tasks in a shared workspace. But there’s a catch. Each product ties the model, runtime, memory, and orchestration to one company’s stack. Most teams won’t use one provider for every job. They may use Claude Code, Codex, OpenCode running locally, and custom agents for internal systems. Making them collaborate with each other and your team usually means building the glue yourself. That is vendor lock-in. Today, we’ll see how to bring humans and agents from different providers into one shared workspace using an open-source coordination layer you can host yourself. Humans can talk directly to agents. Agents can talk to each other. And people can join the conversation, add context, or give further instructions as the work unfolds. The project is called Switch, and it brings this collaboration into Slack, Teams, Discord, Telegram, or Mattermost. You give each agent a role and can work through a Manager. The Manager creates rooms, brings in the relevant agents, carries context between them, and returns the result. In this video, I gave the Manager two incidents. → The inference API started returning 500s after a morning deploy → A recommendation-model training job had been frozen for six hours From one message, it created two linked rooms, brought in a Software Engineer, Architect, and QA Lead, and ran both investigations in parallel. Then the engineer investigating the training failure checked the linked inference room and spotted the same config push behind both failures. The Manager returned one consolidated RCA to the original channel. Throughout the run, I could follow the conversations, give additional instructions, and inspect the underlying agent sessions in Switch Console. That is what I mean by Agents 2.0. Humans and agents working together, sharing context, and contributing as the work unfolds. I build everything locally with Docker and Mattermost and follow the run through to the final handoff. Models will keep changing, so the coordination layer should be able to run separately from any one provider. GitHub: (don't forgot to star 🌟) Chapters: 0:00 Intro 1:12 Installing Switch Console 2:59 Setting up the server & agent providers 4:29 Creating your agents 7:57 Creating a room & adding the manager 9:04 Handing the manager two P0 incidents 9:56 The team spins up incident rooms 11:07 Watching agent sessions in Switch Console 13:48 Investigation results 14:29 Outro Enjoy!

Akshay 🚀

17,345 views • 9 days ago