惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

The GitHub Blog
The GitHub Blog
Martin Fowler
Martin Fowler
Vercel News
Vercel News
U
Unit 42
Engineering at Meta
Engineering at Meta
aimingoo的专栏
aimingoo的专栏
MyScale Blog
MyScale Blog
Y
Y Combinator Blog
阮一峰的网络日志
阮一峰的网络日志
爱范儿
爱范儿
Apple Machine Learning Research
Apple Machine Learning Research
博客园_首页
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
B
Blog RSS Feed
N
Netflix TechBlog - Medium
GbyAI
GbyAI
F
Fortinet All Blogs
MongoDB | Blog
MongoDB | Blog
大猫的无限游戏
大猫的无限游戏
C
Check Point Blog
M
MIT News - Artificial intelligence
D
Docker
IT之家
IT之家
Stack Overflow Blog
Stack Overflow Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
OUT WITH THE OLD IN WITH THE NEW
Alphonce Oyu · 2026-05-25 · via DEV Community

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.