Agentic Development Platform / AI IDE
Google Antigravity is Google's agent-first development platform combining an AI-powered IDE, a standalone agent command center (Antigravity 2.0), CLI, and SDK. It supports autonomous agents that plan and execute multi-step software tasks with browser control, subagents, scheduled tasks, and artifacts. Built on Gemini models with optional Claude and GPT model access.
Browse curated shortlists where this tool appears.
Related picks from editorial notes.
Also mentioned
Full overview from our catalog (read-only reference).
Editorial notes to help compare fit before opening the vendor site.
Context from the listing review and editorial research.
Antigravity launched at Google I/O 2025 and expanded to 2.0 in May 2026, drawing strong interest as Google's answer to Cursor-style agentic IDEs. Early adopters praise agent orchestration; preview status means features and limits may change.
In-depth description and capability notes.
Antigravity IDE — AI-powered editor with tab completion, inline commands, and agent panel Antigravity 2.0 — standalone desktop app for orchestrating parallel agents and projects Browser-in-the-loop agents — agents interact with browsers for UX and testing tasks Antigravity CLI — terminal-first agent interface for shell and coding workflows Antigravity SDK — Python SDK to build custom agents on Google's harness Multi-model support — Gemini 3.x family plus Claude Sonnet and GPT-OSS in agent mode Scheduled tasks and subagents — automate recurring dev workflows
Developers use Antigravity to delegate boilerplate implementation, debugging, and multi-file refactors to agents while reviewing artifacts and verification tests. Enterprise UX teams use browser-control agents to automate repetitive web testing and prototyping tasks.