The Pulse: Antigravity 2.0 takes ‘IDE’ out of its new IDE

2026-06-11 · Source: The Pragmatic Engineer · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Intermediate, medium

Summary

Google recently launched Antigravity 2.0, a significant redesign of its flagship AI IDE, which originally debuted in November 2025 as a clone of Windsurf, acquired for \$2.4B. The new version, Antigravity 2.0, now exists as a distinct application alongside the original "Antigravity IDE" and resembles Codex's desktop app, shifting focus from an IDE to a conversational interface with an "Agent Manager." This transition has created user confusion, particularly with a problematic update process that can replace the IDE version. Feedback highlights numerous issues, including bugs, poor user experience, and limited model support, notably lacking Anthropic's Opus 4.7 and OpenAI's GPT 5.5, while the supported Gemini 3.5 Flash consumes the \$100/month Ultra subscription quota rapidly. Furthermore, Google is replacing the open-source Gemini CLI with the closed-source Antigravity CLI, which lacks Agent Client Protocol (ACP) support and a migration path, forcing users to a less compatible and potentially broken tool.

Key takeaway

For AI Engineers evaluating new development environments, you should approach Google's Antigravity 2.0 and its new CLI with extreme caution. The product's rushed release, reported bugs, confusing dual-app strategy, and forced migration from Gemini CLI suggest significant instability and potential workflow disruption. Consider exploring established alternatives from vendors like Cursor, Anthropic, or GitHub to avoid investing in a rapidly evolving and potentially unreliable ecosystem.

Key insights

Google's Antigravity 2.0 launch introduces a confusing, buggy conversational AI tool, deprecating its IDE and CLI without clear direction or quality.

Principles

• Product launches without clear vision confuse users.
• Rushed development leads to broken user experiences.
• Forcing CLI changes alienates developer communities.

Method

The article describes Google's product launch strategy, which involves deprecating existing tools and forcing users to a new, incomplete version, often without migration paths, to meet internal deadlines.

In practice

• Evaluate new tools for stability before adoption.
• Verify model support and token consumption.
• Seek alternatives from other AI dev tool vendors.

Topics

• AI IDEs
• Google Antigravity
• Developer Tools
• Conversational AI
• CLI Tools
• Product Strategy

Best for: Machine Learning Engineer, NLP Engineer, CTO, AI Engineer, Software Engineer, Director of AI/ML

Related on AIssential

• The Pulse: Antigravity 2.0 takes ‘IDE’ out of its new IDE — The new Antigravity 2.0 IDE faces severe user backlash due to bugs, poor UX, and high Gemini token usage.
• An important update: Transitioning Gemini CLI to Antigravity CLI — Google is unifying its agent development efforts under the Antigravity platform, replacing Gemini CLI with Antigravity CLI.
• Google I/O, Gemini Spark, Antigravity — Google is centralizing its AI agent offerings with Gemini Spark and the Antigravity ecosystem, emphasizing robust enterprise security.
• Agentic app coding gets an upgrade with Google’s release of Android CLI — Android CLI 1.0 enables AI agents to access Android Studio's specialized knowledge for app development.
• Google’s Antigravity Signals a Shift Beyond the IDE — Software development is shifting from human-centric coding in IDEs to agent-driven orchestration and supervision.
• Google launches Antigravity 2.0 with an updated desktop app and CLI tool — Google's Antigravity 2.0 expands agentic coding with desktop, CLI, SDK, and Gemini 3.5 Flash integration.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Pragmatic Engineer.