Google's agent-first development platform - autonomous agents that plan, build, and test across your whole project
Announced at Google I/O 2026, Antigravity is Google's standalone, agent-first development platform. Instead of autocompleting line by line, you describe a task in plain language and autonomous agents plan it, edit across multiple files, and actually run and test the app before handing it back. It is built on Gemini 3.5, and a signature feature is the Browser Subagent: Antigravity spins up a real Chrome window, clicks through your app, takes screenshots, and fixes what is broken - without you ever opening DevTools.
Google's old browser IDE, Project IDX, became Firebase Studio(April 2025), which is now winding down - Google points users toward Google AI Studio(for prompting/prototyping with Gemini) and Antigravity (the agent-first IDE for building real apps). If you want autonomous agents writing and testing code, Antigravity is the current tool.
Go to antigravity.google and download the desktop app for Mac, Windows, or Linux. It is a standalone app (free public preview) - it does not replace your existing editor. There is also an Antigravity CLI and a mobile companion app in preview.
Log in with your Google account. The preview is free for individuals; usage limits scale with your Google AI plan (AI Pro, or AI Ultra for heavy use).
Point Antigravity at a folder (existing repo or a new one). The agents read your whole project as context before they start.
Antigravity supports MCP servers, reusable Skills, and JSON hooks (the same building blocks you learned in Levels 7-8). Add the ones your workflow needs - e.g. GitHub, a database, or your issue tracker.
Here is the full agent-first loop on a small but real project - the same shape you would use for a feature at work.
In the Agent Manager, give a single high-level task:
Antigravity returns a plan before writing code. You approve or tweak it:
The agent writes the files, then the Browser Subagent opens the app and actually uses it: types a task, clicks add, toggles it done, deletes one, refreshes the page to confirm it persists. It captures screenshots at each step. If "delete" does not work, it sees the failure, fixes app.js, and re-tests - on its own.
You get the working app plus screenshots and a test summary. Send one follow-up to refine:
The current tool is highlighted. There is no single winner - pick by how you like to work.
| Tool | Type | Pricing | Best for | Models / AI |
|---|---|---|---|---|
| GitHub Copilot | IDE extension | Free tier; Pro ~$10/mo | AI in your existing editor | GPT-5.5, Claude Sonnet 4.6, Gemini 3.5 |
| Cursor | AI IDE (VS Code fork) | Hobby free; Pro $20/mo | All-round AI editor + agent | GPT-5.5, Claude Opus 4.8 / Sonnet 4.6 |
| Windsurf | AI IDE (VS Code fork) | Free tier; paid plans | Agentic flows (Cascade) | Frontier models + own |
| Google Antigravity(this page) | Agent-first IDE | Free public preview | Autonomous build + browser test | Gemini 3.5 |
| Claude Code (CLI) | Terminal agent | Claude sub or API | Agentic coding in the terminal | Claude Opus 4.8 / Sonnet 4.6 / Haiku 4.5 |
| VS Code + AI ext | Editor + extensions | Free options exist | Keep VS Code, add AI | Depends on extension |
Pricing and model support change often. Verified June 2026 - confirm on each tool's official site.
Go deeper on the skills this tool is for:
Links open the official sites. Pricing and features change often - always confirm there. (Verified June 2026.)