Antigravity: Google's Agentic Code Editor

Official Sources

The Team Behind Antigravity

Antigravity marks the first release from a team that originated at Windsurf. After selling non-exclusive IP rights, the founding members joined Google and built this product on top of that foundation. The result is an editor that feels familiar if you have used VS Code, Cursor, or similar forks, but introduces several new abstractions for agent interaction and testing.

For the larger agent workflow map, read AI Agents Explained: A TypeScript Developer's Guide and How to Build AI Agents in TypeScript; they give the architecture and implementation context this piece assumes.

Getting Started

Antigravity is currently in public preview and available to try for free. Given the attention it has received, expect rate limits during this phase. The interface opens to an agent manager that serves as your central coordination hub.

The agent manager contains an inbox where you can spawn different agents and see which ones require attention. If you work across multiple workspaces or projects, you can coordinate everything from this view. When you are ready to dive into code, press Command+E or click the editor button in the top-right corner.

Once you add a directory, it appears on the left side. A dropdown lets you toggle between workspaces and start new conversation threads for each agent. You can add images to your prompts and use @mentions as you would expect.

Models and Modes

Antigravity offers two distinct modes: planning mode and fast mode. The model selection includes Gemini 3 Pro (high and low configurations), Claude Sonnet 4.5, and surprisingly, GPT-OSS 120. The first two represent some of the best models available. The inclusion of OpenAI's open-source model, while notable, is an odd choice given its limited adoption in coding contexts. Notably absent is GPT-5, which is understandable for competitive reasons.

Fast Mode in Action

When you submit a request in fast mode, the agent immediately begins working through the task. You can watch it spawn work, create files, and build out the application in real-time.

One standout feature is automatic testing. Without any prompting, Antigravity opens your application in a preview and begins testing it. The agent navigates through the interface, clicks buttons, scrolls, and validates functionality on your behalf.

This browser automation shows you exactly what is happening: mouse movements, hover states, button clicks, and scroll actions. The agent reasons between each step, explaining what it is doing and why. This level of integrated testing is rare in local development tools. While Devon and Emergent Labs offer similar capabilities, this is the first time such thorough automated testing has been built directly into a mainstream IDE interface.

Planning Mode for Complex Projects

For more involved work, planning mode changes the workflow. Instead of immediately executing, the agent develops a structured plan first. You can review this plan and leave comments on individual tasks or planning stages before execution begins.

This creates additional surface area for interaction. You can skip steps, modify requirements, or provide feedback on specific parts of the plan. The comment system also works with images you pass in, letting you give precise visual feedback.

Integrated Image Generation

Antigravity incorporates Nano Banana directly into the product. You can generate images within the same interface where you build applications. For example, you might generate a reference image of a plant store landing page with specific styling requirements, then ask the agent to build a Next.js application based on that visual reference.

The image generation is currently rate-limited, but the integration points toward a future where visual design and code generation happen in the same workflow.

The IDE Experience

Opening the full editor reveals an environment that will feel familiar to VS Code or Cursor users. Your agent conversation sits on the right side, and you can continue sending edits and refinements just as you did with the initial prompt.

The ability to hop between the agent manager, preview mode, and full IDE creates a flexible workflow. You can start with a high-level request, watch the agent build and test the application, then drop into the editor for fine-tuning.

Video Context and Future Possibilities

Gemini 3 Pro supports video input, which opens interesting possibilities for future workflows. Feeding video context directly into the agent could enable new forms of interaction, such as recording a bug and having the agent diagnose it from the footage, or capturing a design walkthrough and translating it into implementation tasks.

Bottom Line

Antigravity brings together several capabilities that were previously scattered across different tools: multi-agent management, automatic browser testing, integrated image generation, and structured planning workflows. The VS Code foundation means developers can adopt it without learning an entirely new environment, while the agent-centric features push beyond what existing AI-powered editors offer.

For developers already using AI coding assistants, the automated testing and planning mode alone justify exploring the preview. The question remains how Google will price these capabilities once the preview period ends.

---

FAQ

What is Antigravity and who built it?

Antigravity is Google's agentic code editor built by the team that originally created Windsurf. After selling non-exclusive IP rights to Codeium, the founding members joined Google and built Antigravity on top of that foundation. The result is a VS Code-style IDE with native agent orchestration, automatic testing, and planning workflows.

How does Antigravity compare to Cursor?

Both editors are VS Code forks with AI assistance, but Antigravity adds several capabilities Cursor lacks: an agent manager for coordinating multiple agents across workspaces, automatic browser testing that runs without prompting, and a planning mode with comment-based feedback. Cursor focuses on inline code completion and chat, while Antigravity leans heavily into multi-agent orchestration and QA automation.

What models does Antigravity support?

Antigravity supports Gemini 3 Pro (high and low configurations), Claude Sonnet 4.5, and GPT-OSS 120. GPT-5 is notably absent, likely for competitive reasons. Model selection is available in both fast mode and planning mode.

What is the difference between fast mode and planning mode?

Fast mode executes immediately - the agent starts working, creates files, and builds the application in real-time with automatic testing. Planning mode generates a structured plan first, letting you review, leave comments on individual tasks, skip steps, or modify requirements before execution begins. Planning mode is better for complex projects where you want oversight before changes are made.

How does Antigravity's automatic testing work?

Antigravity opens your application in a preview and tests it without any prompting. The agent navigates the interface, clicks buttons, scrolls, hovers, and validates functionality. You can watch the mouse movements and see the agent's reasoning between each step. This level of integrated browser automation was previously only available in tools like Devin and Emergent Labs.

Can I generate images inside Antigravity?

Yes. Antigravity integrates Nano Banana directly into the product for image generation. You can generate reference images within the editor and use them as visual prompts for the coding agent. This is rate-limited during the preview phase.

Is Antigravity free?

Antigravity is currently in public preview and free to try. Expect rate limits during this phase. Google has not announced pricing for when the preview period ends.

Does Antigravity support video input?

Gemini 3 Pro supports video input, which opens possibilities for future workflows like feeding a bug recording directly to the agent for diagnosis, or capturing a design walkthrough and translating it into implementation tasks. This capability is available through the underlying model but the full workflow integration is still evolving.

---

Watch the Video

Related apps

• CLI Directory - Directory of 50+ CLI tools for developers. Search, filter, and compare.
• DD Orchestrator - Describe any goal, agents coordinate and ship it.

Related

• Subscribe to DevDigest on YouTube for hands-on walkthroughs