Five surfaces onto the same agents
Antigravity is a platform with several front doors. Knowing which door you are standing in explains most of the confusion about what it can do.
On this page
The five surfaces, what artifacts are, what you can bolt on, and how far the agent is allowed to go.
Names are Google's, from antigravity.google and antigravity.google/docs, read 30 August 2026. Descriptions are ours.
Where the name stopped being accurate
It launched as an IDE. It is now five things, and the IDE is only one of them.
The November 2025 launch described two views — an editor for synchronous work and a manager for spawning and watching agents run asynchronously across workspaces. That framing still explains the product better than the current product page does.
What has changed since is the number of doors into the same agents: a command centre for parallel local runs, a terminal surface, a Python SDK for building your own, and extension support for editors you already use. Underneath, it is a heavily modified fork of Visual Studio Code — with an open question, noted on Wikipedia, about whether it forks VS Code directly or forks Windsurf.
Surfaces — Five ways in, not one application
5 entriesAntigravity IDE
The full agentic editor: tab autocompletion, natural-language commands and an agent that operates across the editor, terminal and browser.
Antigravity 2.0
Google's phrase for it is a command centre — managing several local agents running in parallel rather than one conversation at a time.
Antigravity CLI
A terminal-first surface for the same agents, for people who would rather not leave the shell.
Antigravity SDK
A Python kit for prototyping custom agents against the platform.
Antigravity Extensions
Extension support, so an existing editor set-up carries over.
Artifacts — What the agent hands back instead of a log
5 entriesImplementation plans
The agent writes the plan before it writes the code, so the thing you review is the intent rather than the diff.
Task lists
Work broken into steps you can follow while it runs.
Screenshots
Visual evidence that the change did what it said, captured by the agent.
Browser recordings
A replay of the agent driving the browser — the strongest form of verification the platform produces.
Artifact review
Comments and feedback can be left on any artifact to steer the next pass.
Customisation — What you can bolt on
6 entriesMCP servers
Model Context Protocol connections to tools and data outside the editor.
Skills
Packaged procedures the agent can call for a particular kind of task.
Rules
Standing instructions that apply to a project without being retyped.
Plugins
Bundles that install a set of the above together.
Hooks
Points where your own code runs in response to what the agent does.
Sidecars
Companion processes running alongside the agent.
Agent capabilities — How far it is allowed to go
6 entriesSlash commands
Named shortcuts for specialised tasks, typed into the same chat input.
Teamwork
Several agents working the same repository without treading on each other.
Permissions
The controls that decide what the agent may do unattended.
Subagents
An agent delegating part of a task to another agent.
Worktree mode
Starting a run in a fresh git worktree instead of your working copy — the difference between an experiment and an edit.
Remote control
Reaching a running agent from somewhere other than the machine it is on.
Worth knowing
Google describes the agent as able to operate autonomously across your editor, terminal and browser — writing code, running commands, testing in a browser and implementing fixes without continuous human intervention. The permissions surface is where you decide how much of that you actually want.