Google I/O happened last week and there are a lot of new products coming from google. The main theme of the conference was based on artificial intelligence. Honestly speaking, in this current time is there anything in the tech world that is not built around AI. We all know of the controversial AI bubble and how its bust will affect the tech ecosystem.
All that aside, I noticed something new from Google. They are integrating Gemini CLI into the Antigravity 2.0 CLI tool. Let me break down what this means. First of all you need to understand that as of June 18, 2026 Gemini CLI and Gemini Code Assist IDE extensions will stop serving requests for Google AI pro and Ultra, as well as for those using the free version.
The transition is actually smooth. It only takes the simple use of following commands in your terminal depending on the system software you’re using.
Microsoft windows
Windows Powershell;
irm https://antigravity.google/cli/install.ps1 | iex
Windows CMD ;
curl -fsSL https://antigravity.google/cli/install.cmd -o install.cmd && install.cmd && del install.cmd
macOs | Linux
curl -fsSL https://antigravity.google/cli/install.sh | bash
After running the commands on your terminal, you can open the CLI by running the command ‘aggy’ on your terminal. You will follow the simple setup steps and authentication procedures.
TECHNICAL UPDATES
Gemini CLI proved that the terminal is the perfect environment for agentic tasks. This claim can be backed by the millions of users of the tool. The community boasts of over 100,000 GitHub users, 6,000 merged pull requests , and hundreds of contributors. This is according to Dmitry Lyalin Group Product Manager and Taylor Mullen Principal Engineer ; here’s the link https://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/link
Migrating from Gemini CLI;
On the first launch of Antigravity CLI, you should see Migration Options where you have a choice of migrating your existing Gemini CLI extensions to the equivalent Plugins.
You should note that some of the features of Gemini CLI cannot be migrated 1 to 1 for example custom themes are not currently supported .
Gemini CLI launched extensions, a way to extend the CLI by sharing capabilities. The industry has now moved to a fancy name “Plugins”. A plugin is just an add-on, for technicality it is a software component that adds new features or custom functionality to an existing program without altering the core software.
Users should be prompted on the first launch of Antigravity CLI to have their extensions mitigated to plugins.
This can also be simply done by running a command on the terminal;
‘agy plugin import gemini’
Running the command will search for each locally installed extension and convert them to an Antigravity plugin.
RULES(context files)
Antigravity CLI supports the following context files:
Workspace Context: It reads both Gemini.md and Agents.md from your active workspace directory.
Global Context:Automatically loads and enforces loads and enforces global constraints located at ‘’~/.gemini/GEMINI.md’
AGENTIC SKIllS
Agentic skills work the same to the way it worked on Gemini CLI. They are managed with the same /skills command and are also converted to slash commands allowing them to be invoked manually.
Global skills for Gemini CLI are shared with Antigravity CLI across all workspaces. There is no action needed for workspaces; they are picked up automatically.
Note that Antigravity CLI workspace-specific skills are stored in ‘.agents/skills’, so if you have any project/workspace skills in a given project in the Gemini CLI ‘.gemini/skills’ folder, it will have to be moved.
MCP Servers
Antigravity supports both local and remote MCP servers and provides the same /MCP command to manage them. The main difference between Gemini CLI and Antigravity CLI is the file location where mcp servers are defined.
Antigravity and Antigravity CLI both store MCP configurations in a mcp_configuration.json file while Gemini CLI stores them inline in the systems settings.json.
Note: All the work presented here has been referenced from the official blog by Google on the migration so its factual research.
Top comments (1)
This is a great breakdown of a dilemma almost every team faces. The 'out with the old' mentality is always exciting at the start of a project, but it’s so important to remember Chesterton’s Fence—understanding why the old code was written that way before ripping it out. Rearchitecting from scratch feels great until you realize the 'crusty old code' was quietly handling dozens of obscure edge cases and business logic quirks. Balancing modern stack upgrades while respecting the institutional knowledge built into the legacy system is the real superpower.