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

T
The Exploit Database - CXSecurity.com
V
Vulnerabilities – Threatpost
Google DeepMind News
Google DeepMind News
Attack and Defense Labs
Attack and Defense Labs
Webroot Blog
Webroot Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
TaoSecurity Blog
TaoSecurity Blog
I
Intezer
Application and Cybersecurity Blog
Application and Cybersecurity Blog
N
News | PayPal Newsroom
S
Security Affairs
T
Tor Project blog
P
Proofpoint News Feed
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
S
Security @ Cisco Blogs
H
Heimdal Security Blog
Hacker News: Ask HN
Hacker News: Ask HN
Help Net Security
Help Net Security
U
Unit 42
云风的 BLOG
云风的 BLOG
The Hacker News
The Hacker News
Cisco Talos Blog
Cisco Talos Blog
量子位
F
Full Disclosure
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 叶小钗
有赞技术团队
有赞技术团队
T
Troy Hunt's Blog
P
Privacy & Cybersecurity Law Blog
Forbes - Security
Forbes - Security
人人都是产品经理
人人都是产品经理
L
Lohrmann on Cybersecurity
Apple Machine Learning Research
Apple Machine Learning Research
Microsoft Security Blog
Microsoft Security Blog
博客园 - Franky
腾讯CDC
AI
AI
Last Week in AI
Last Week in AI
Latest news
Latest news
Google Online Security Blog
Google Online Security Blog
N
Netflix TechBlog - Medium
Engineering at Meta
Engineering at Meta
GbyAI
GbyAI
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
IT之家
IT之家
Martin Fowler
Martin Fowler
Blog — PlanetScale
Blog — PlanetScale
V2EX - 技术
V2EX - 技术
酷 壳 – CoolShell
酷 壳 – CoolShell

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 Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python) The Hidden Cost of AI Systems Nobody Talks About. undefined vs undeclared, and how typeof behaves Switching from file-based jobs to NATS/Kafka in Rust without changing code io_uring Adventures: Rust Servers That Love Syscalls Why Agentic AI is Killing the Traditional Database The POUR principles of web accessibility for developers and designers Quantum Neural Network 3D — A Deep Dive into Interactive WebGL Visualization How To Install Caveman In Codex On macOS And Windows Automation Pipeline Reliability: Why Your Workflow Breaks When Nobody Is Watching I Built an 'Open World' AI Coding Agent — It Works From ANY Folder From Freelancing to Product: A Tech Service Company's SaaS Transformation China's AI Giants: Adding Tencent Hunyuan & ByteDance Doubao to AI University (74 Providers) On the Vibe Coders and Their Lies clerk: Auto-Summarize Your Claude Code Sessions AI Weekly — 2026/04/10–04/17 | The Model Lockdown Is Here, but the Toolchain Is the Real Battleground AI 週報 — 2026/04/10–2026/04/17 模型封鎖潮來了,但工具鏈才是真戰場 Maybe this is how Open-Source apps are born... 🚀 Fine-Tune LLMs with LoRA and QLoRA: 2026 Guide tRPC v11 + Next.js App Router: End-to-End Type Safety Without the Boilerplate ShadCN UI in 2026: Why I Stopped Installing Component Libraries and Started Owning My Components SaaS Billing in React Server Components: Stripe + Supabase Without a Single `useEffect` Join our DEV Weekend Challenge — $1,000 in Prizes Across TEN winners! Submissions Due April 20 at 6:59 AM UTC. Implementing FSRS Spaced Repetition in Flutter + Supabase — Adding Memory Science to an AI Learning App "I Texted My Localhost From the Train — Claude Code Fixed the Bug Before I Got Home" I Built a Sales Prep AI and It Went Deeper Than Expected Design to Code #2: One JSON, Eleven Outputs Solving the 100M-Row Problem: A Summary Table Pattern for High-Volume Push Notification Logs Flutter Web With Wasm: What Actually Changes For Developers I Built 50 Royalty-Free Soundtracks for My Side Project in a Weekend Using AI Music Generation The Vibe Coding Security Checklist: 7 Things to Check Before You Ship Stop Letting Googlebot Guess Fix Your React App's SEO Right Desconstruindo o Streaming do LinkedIn: Como Criar um Engine de Extração de Vídeo de Alta Performance com HLS e FFmpeg (EDA Part-1) EDA (Exploratory Data Analysis) Explained With Real Life — Why Looking at Your Data Is the Most Important Step in Machine Learning Brand Relationship Management at Scale: Our 4-Touch Outreach System for 200+ Brands Why String.fromEnvironment() Might Return an Empty String in Dart JGuardrails 1.0.0 — Hardening Java LLM Apps Against Jailbreaks, Toxicity, and Prompt Injection Plan and Schedule a Full Week of Threads Content From One Claude Conversation Coding Cat Oran Ep3, Five Tables Changed Everything Updated: BFF Pattern I'm done watching freelancers get buried by 200 proposals. So I'm building the alternative. This is my first post BFS Algorithm in Java Step by Step Tutorial with Examples Tracking LLM Pricing Monthly: An Open Dataset for 22 AI Models How We Measure Content ROI on a Comparison Site: Revenue Attribution Without Perfect Data Introducing Nova AI Ops: The AI-Native Operating System for SRE Teams I built a free desktop video downloader for Windows — Grabbit How Talkie OCR Helps Vision-Impaired & Dyslexic Users Read the World Around Them VRCFaceTracking安装和iPhone面捕配置教程,有bug Even CrowdStrike Can't See Your Agents The Automation Gold Rush: What n8n Workflows and Claude Are Opening Up for Developers Right Now
Using Google's New AI Command-Line Assistant: Antigravity CLI (agy) and YOLO's No-Confirmation Mode
Evan Lin · 2026-05-27 · via DEV Community

image-20260526212403006

Background

With generative AI entering daily development, the AI assistant in the terminal has also ushered in an epic update! If you are a loyal supporter of the original Gemini CLI, you may already know that this tool will be officially retired on June 18, 2026.

Taking over the torch of this era is Google's stunning launch at I/O 2026, the next-generation lightweight, Go language-driven multi-agent terminal UI assistant —— Antigravity CLI (called agy in the terminal)!

However, the launch of new tools is always accompanied by various pitfalls and surprises. This article will focus on Antigravity CLI (agy), revealing how to deal with the "invisible color scheme hell", how to enable the addictive YOLO no-confirmation frenzy mode, and those terminal black technologies and setting secrets hidden deep within settings.json!

image-20260526212808645


🛠️ Step 1: Antigravity CLI (agy) Color Scheme Savior for Invisible Text!

When installing and launching agy for the first time, the first blow that many developers accustomed to macOS / Linux dark background terminals usually face is: "The font is all black, and the text is completely invisible!"

This is because the agy default configuration file may be configured with a light (Light) theme. We don't need to compromise and change our favorite terminal background, just modify settings.json and it can be saved with one click!

🛠️ Steps to Fill the Pit

  1. Find the global configuration file for Antigravity CLI, the path is usually: ~/.gemini/antigravity-cli/settings.json

  2. Modify the "colorScheme" setting value from "light" to "dark":

  3. After saving the file and restarting the terminal, all outputs will automatically convert to a high-contrast dark mode color scheme, and your eyes will be saved instantly!


🔥 The Main Event: YOLO Mode —— Unlock the "No Confirmation" Ultimate Move for Unlimited Automated Execution

image-20260526212326057

When using AI to write code, the most annoying thing is that every time you make a file modification and execute a git command, the CLI will pop up a question: "Are you sure you want to perform this operation? (y/N)". This is simply a double torment of fingers and spirit when performing large-scale refactoring or batch tasks.

To this end, agy provides two levels of YOLO (You Only Live Once) no-confirmation automatic execution mode, allowing AI to smoothly and continuously execute autonomously until the task is completed:

1. ⚡ Extreme YOLO: --dangerously-skip-permissions Parameter

If you are in a completely isolated and secure sandbox environment, or have 100% confidence in the instructions generated by AI, you can add this ultimate move when starting:

agy --dangerously-skip-permissions

Once this Flag is added, agy will completely skip all tool authorization and command execution confirmation prompts, and enter an "all the way to the top" automatic execution state. Suitable for letting it run complex automated tests or file migrations on its own!

2. 🛡️ Moderate Control: /permissions Fine-grained Settings

If you don't want to risk the AI executing rm -rf, you can directly enter /permissions in the CLI or directly modify settings.json. Through a whitelist mechanism, only specific commands or paths are automatically approved:

{
  "permissions": {
    "allow": [
      "read_file(/Users/al03034132/Documents)",
      "command(git)",
      "command(npm test)"
    ],
    "deny": [
      "command(rm -rf)"
    ]
  }
}

This way, you can allow Git operations and unit tests to enter the YOLO no-confirmation state, while also ensuring the security of the core file system!


🤫 Those Unknown agy Black Technologies and Setting Secrets

As Google's latest official Code-first agent weapon, agy also has several hidden functions deep within the configuration file and commands, which are rarely seen in newspapers:

🧩 1. Asynchronous Subagents

This is definitely agy's most revolutionary multi-agent architecture! You can directly call multiple subagents in the terminal to run complex tasks in the background:

  • For example: one subagent goes online to check the latest API documentation, one runs unit tests in the background, and one performs code refactoring.
  • And your main terminal will not be blocked at all! You can enter /agents to monitor the health and execution progress of all subagents in the background at any time.

🧠 2. Change Brains at Any Time: /model Secret

agy not only supports the Gemini series models on Vertex AI, but if you need to, you can also use the built-in /model slash command to directly switch seamlessly between Gemini, Claude, and even other open-source models with one click, helping you verify the same bug with different thinking models, which is super convenient!

🛡️ 3. Multi-Operating System Level Security Sandbox (Terminal Sandbox)

In order to prevent AI from running out of control malicious code in YOLO mode, agy silently implements operating system level sandbox protection at the bottom!

  • nsjail isolation will be automatically enabled on Linux.
  • macOS will automatically call the system's native sandbox-exec.
  • Even if AI writes a script that pollutes the file system, it will be perfectly confined in the sandbox and unable to move!

📦 4. Upgrade Old Things: Seamless Migration Mechanism from Gemini CLI

Although Gemini CLI has gone down in history, agy has thoughtfully designed a "one-click import tool". When you start agy for the first time, it will automatically scan the old configuration path and perfectly align and migrate your original plugins, custom skills, and settings.json accumulated in Gemini CLI!


Summary and Suggestions

The upgrade from Gemini CLI to Antigravity CLI (agy) is not just a change in the command line name, but a leap forward from single-model question and answer to Multi-Agent Workflows.

By properly setting permissions in settings.json, combined with the no-confirmation function of YOLO mode, developers can allow AI to automatically and smoothly complete various medium and large tasks while ensuring the security of the host.

Quickly open your terminal and enter agy --dangerously-skip-permissions to experience this futuristic development artifact! See you next time for the actual combat!