Google Antigravity
@antigravity
An agentic development platform evolving the IDE into the agent-first era @GoogleDeepMind
17 Following 175.3K Followers
Antigravity is being used for research eval analysis.
Instead of manually writing scripts and parsing tables, researchers can now analyze evals in minutes using natural language enabled by skills. Antigravity performs the quantitative analysis, proposes hypotheses, and spins up dynamic subagents in parallel to isolate the failure modes.
Show more
Gemini 3.6 Flash is live in Antigravity! ⚡️
Building on 3.5 Flash feedback, it consumes up to 17% fewer output tokens while completing complex workflows in fewer reasoning steps and tool calls.
Show more
We’ve built a new way to ship software: Agent Teams in Antigravity.
Just run /teamwork-preview to spin up a dynamic team of specialized subagents. They coordinate in the background to plan, build, and verify complex engineering tasks in parallel.
Show more
What are the core primitives powering Antigravity in 2026?
Kevin Hou breaks down why we’re investing in dynamic agent teams, active sidecars, and generative UI to build the future of autonomous engineering.
Show more
The latest Antigravity 2.0 update includes a new built-in Antigravity Guide skill, audio file rendering, and improved substring file search.
Check the changelog for all the updates
Show more
Napkin sketch to interactive 3D rendering!
Antigravity is the agentic development platform for developers to turn hand-drawn sketches into fully functional 3D learning modules.
Show more
Keep your Antigravity workflow unified. Sync conversations in Antigravity 2.0 with Antigravity CLI by simply confirming the import.
Start a conversation in Antigravity and pick up where you left off in Antigravity CLI 💫
As of yesterday's v1.0.4 release of the CLI you can now easily resume your sessions from @antigravity !
Just run /resume and then tab over to the Antigravity tab to see and import your conversations. 🪄
Show more
We’re transforming Google Antigravity into a scientific workbench. The new Science Skills bundle allows researchers to run complex workflows like protein analysis in minutes using specialized Alpha* models and 30+ major scientific databases.
Show more
How powerful is Gemini 3.5 Flash?
In a recent research preview, we pushed it to the extreme, powering 93 subagents across 15,314 model calls that wrote a custom kernel, filesystem, and drivers from scratch. 12 hours later, it booted Doom. 🖥️
This is just a glimpse of the model's reasoning depth and code generation capabilities. Full breakdown below 👇
Show more
