An important update: Transitioning Gemini CLI to Antigravity CLI

· Source: Google Developers Blog - AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Robotics & Autonomous Systems · Depth: Intermediate, short

Summary

Google is transitioning its Gemini CLI to the new Antigravity CLI, effective May 19, 2026, to support multi-agent workflows and a unified backend. The original Gemini CLI, launched in 2025, garnered millions of users and over 100,000 GitHub stars, but user needs evolved beyond its initial capabilities. Antigravity CLI, built in Go for faster execution and asynchronous workflows, integrates with Google Antigravity 2.0, a premier agent-first development platform. Key features like Agent Skills, Hooks, Subagents, and Extensions (now Antigravity plugins) are preserved. For consumers, Gemini CLI and Gemini Code Assist IDE extensions will cease serving requests on June 18, 2026, for Google AI Pro, Ultra, and free users. Enterprise customers with Gemini Code Assist Standard or Enterprise licenses, or those using Gemini Code Assist for GitHub through Google Cloud, will retain access to Gemini CLI and its associated services.

Key takeaway

For AI Architects and developers building agentic applications, you should immediately evaluate Antigravity CLI and plan your migration from Gemini CLI. Consumer access to Gemini CLI will end on June 18, 2026, necessitating a prompt transition to Antigravity CLI to maintain workflow continuity and leverage multi-agent capabilities. Enterprise users retain Gemini CLI access but can explore Antigravity CLI with Google Cloud projects.

Key insights

Google is unifying its agent development efforts under the Antigravity platform, replacing Gemini CLI with Antigravity CLI.

Principles

Method

Transition from Gemini CLI to Antigravity CLI involves migrating existing features like Agent Skills and Hooks to Antigravity plugins, leveraging a Go-based architecture for performance and asynchronous multi-agent orchestration.

In practice

Topics

Code references

Best for: CTO, VP of Engineering/Data, AI Architect, AI Engineer, Machine Learning Engineer, Director of AI/ML

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Google Developers Blog - AI.