亲身体验 Antigravity CLI

mkdir agy-cli-projects

cd agy-cli-projects

curl -fsSL https://antigravity.google/cli/install.sh | bash

irm https://antigravity.google/cli/install.ps1 | iex

curl -fsSL https://antigravity.google/cli/install.cmd -o install.cmd && install.cmd && del install.cmd

% curl -fsSL https://antigravity.google/cli/install.sh | bash
⠋ Detecting system environment...
✓ Platform detected: darwin_arm64
⠋ Querying release repository...
✓ Latest available version: 1.0.1
⠋ Downloading release package...
✓ Download complete and checksum verified.
⠋ Extracting binary from archive...
⠋ Configuring shell environment...
I0523 11:44:14.012088 76528 installer.go:27] Running Antigravity CLI setup...
Warning: /Users/neilirani/.local/bin is not present in your active PATH.
To use the 'agy' CLI globally, please manually add it to your shell profile:
 echo 'export PATH="/Users/yourusername/.local/bin:$PATH"' >> ~/.zshrc && source ~/.zshrc
✅ Antigravity CLI binary placed successfully at /Users/yourusername/.local/bin/agy
Note: The binary is installed, but it is not in your active PATH. Please follow the instructions above to add it, then restart your terminal session.

$ agy --version
1.0.7

    ▄▀▀▄
   ▀▀▀▀▀▀
  ▀▀▀▀▀▀▀▀
 ▄▀▀    ▀▀▄
▄▀▀      ▀▀▄

Welcome to the Antigravity CLI. You are currently not signed in.

Select login method:
> 1. Google OAuth
  2. Use a Google Cloud project

[Use arrow keys to navigate, Enter to select]

Accessing workspace:

/Users/yourusername/agy-cli-projects

Do you trust the contents of this project?

Antigravity CLI requires permission to read, edit, and execute files here.

> Yes, I trust this folder
 No, exit

 ↑/↓ Navigate · enter Confirm

Give me a famous quote on Artificial Intelligence and who said that?

  Here is a famous quote on Artificial Intelligence:                                                                           
                                                                                                                               
  │ "Artificial intelligence is the new electricity."                                                                          
  │ — Andrew Ng                                                                                                                

Settings
  Search:  
          ────────────────────
> Animation Speed      medium
  Artifact Review      asks for review
  Color Scheme         dark
  Editor               auto ($EDITOR)
  Enable Telemetry     on
  Non-Workspace Access off
  Notifications        off
  Rendering Mode       native terminal (inline)
  Sandbox Mode         off
  Show Feedback Survey on
  Show Tips            on
  Tool Permission      request-review
  Use AI Credits       off
  Verbosity            high

{
      "colorScheme": "dark",
      "model": "Gemini 3.5 Flash (High)",
      "statusLine": {
        "type": "",
        "command": "",
        "enabled": true
      },
      "trustedWorkspaces": [
        "/Users/romin/antigravity-cli-projects",
        "/Users/romin/agy-cli-projects"
      ]
    }

 Tool Permission
  > request-review (current)
    proceed-in-sandbox
    always-proceed
    strict

agy --help

agy -p "What is the gcloud command to deploy to Cloud Run"

agy models

agy --model "Gemini 3.5 Flash (Low)"

agy --dangerously-skip-permissions

> get the latest news and write it in a file called news.txt. Then create another file that contains the summary of that file.

● ListDir(/Users/romin/agy-cli-projects)
● WebSearch(latest world news May 24 2026 news headlines) (ctrl+o to expand)

▸ Thought for 2s, 95 tokens
 Processing News Information

● Create(/Users/romin/agy-cli-projects/news.txt)
● Create(/Users/romin/agy-cli-projects/summary.txt) (ctrl+o to expand)

 I have fetched the latest world news headlines and created the requested files in your workspace:                                                                  
                                                                                                                                                                    
 1. news.txt: Contains the detailed news headlines for today (May 24, 2026), including topics on geopolitics (U.S.-Iran negotiations, Ukraine conflict), U.S. 
 security incidents, the Ebola outbreak in Central Africa, and the passing of NASCAR champion Kyle Busch.                                                           
 2. summary.txt: Contains a concise, structured summary of the major categories covered in the news file.                                                        

Please build a web application for me using Python Flask and plain vanilla HTML, JavaScript and CSS that fetches the BigQuery Release notes from (https://docs.cloud.google.com/feeds/bigquery-release-notes.xml) and shows them to me. 

A simple refresh button with a spinner is good enough, anytime I'd like to refresh the details. 

I would also like the ability to take any specific update, select it and then Tweet about it.

I will start by exploring the workspace to see if there is an existing structure or if this is a brand new project.                                                                   

● ListDir(/Users/romin/agy-cli-projects/bq-release-notes) (ctrl+o to expand)

 I will read the BigQuery release notes XML feed to understand its structure (Atom/RSS elements, entry/item elements, namespaces, dates, titles, content) so that we can parse it      
 correctly in the Python Flask backend.                                                                                                                                                

● ReadURL(https://docs.cloud.google.com/feeds/bigquery-release-notes.xml) (ctrl+o to expand)

 I will view the fetched feed content saved locally to understand its format and structure.                                                                                            

● Read(/Users/romin/.gemini/antigravity-cli/brain/116191af-e6ea-4ba5-aa23-62f995bd068a/.system_generated/steps/6/content.md) (ctrl+o to expand)

▸ Thought for 2s, 2.3k tokens
 Analyzing XML Feed Structure
 I will write the implementation plan detailing the architecture, design aesthetic, components, and verification steps for the BigQuery Release Notes Web Application. This plan will be
 written to the artifacts directory.                                                                                                                                                   

● Create(/Users/romin/.gemini/antigravity-cli/brain/116191af-e6ea-4ba5-aa23-62f995bd068a/implementation_plan.md) (ctrl+o to expand)

 I have created the implementation_plan.md to outline the design and architecture of the BigQuery Release Notes Web Application.
                                                                                                                                                                                       
 Please review the plan, especially the approach for the Twitter Composer & Preview Card, and let me know if you approve or if there are any adjustments you'd like to make!           

                                                                                                                                                           1 artifact · /artifact to review

Create a .gitignore file for this project.

Great! I would now like to push all of this to a new repository in my GitHub account. I would like to name this repository <Your-Name>-event-talks-app

Create the following folders "Images","Documents","Videos"

Go through all the files in this folder and then organize them by moving all the files ending with .jpg, .jpeg, .gif into the "Images" folder. Move all ".txt" files into the "Documents" folder. Move all the ".mp4" files in the "Videos" folder.

I have completed organizing your files into their respective folders. Here is a summary of the files moved:                                          
                                                                                                                                                       
  • Images: Moved 95 files ending in  .jpg  or  .jpeg  (no  .gif  files were present).                                                         
  • Documents: Moved 1 file ending in  .txt  ( 12March_Live_chat_transcript.txt ).                                                                
  • Videos: Moved 26 files ending in  .mp4 .

The current folder contains a list of invoice files in Image format. Go through all the files in this folder and extract the following invoice information in the form of a table: Invoice No, Invoice Date, Invoice Sent By, Due Date, Due Amount.

list all files with .png extension in this folder. Extract the invoice information from it by reading them locally and display it in a table format containing the following column headers: : Invoice No, Invoice Date, Invoice Sent By, Due Date, Due Amount. Add a column at the end of the table that shows a red cross emoji in case the due date is in the past.

Generate a JSON array of 3 synthetic customer reviews for a new smartphone. Each review should have 'reviewId' (string, UUID-like), 'productId' (string, e.g., 'SMARTPHONE_X'), 'rating' (integer, 1-5), 'reviewText' (string, 20-50 words), and 'reviewDate' (string, YYYY-MM-DD format).

Generate a JSON array representing 7 daily sales records for a mock API endpoint. Each record should include 'date' (YYYY-MM-DD, chronologically increasing), 'revenue' (float, between 5000.00 and 20000.00), 'unitsSold' (integer, between 100 and 500), and 'region' (string, either 'North', 'South', 'East', 'West').

Generate 5 SQL INSERT statements for a table named 'users' with columns: 'id' (INTEGER, primary key), 'username' (VARCHAR(50), unique), 'email' (VARCHAR(100)), 'password_hash' (VARCHAR(255)), 'created_at' (DATETIME, current timestamp). Ensure the password_hash is a placeholder string like 'hashed_password_X'.

Generate 10 lines of CSV data, including a header row, for customer transactions. Columns should be: 'TransactionID' (unique string), 'CustomerID' (integer), 'ItemPurchased' (string, e.g., 'Laptop', 'Monitor', 'Keyboard'), 'Quantity' (integer, 1-3), 'UnitPrice' (float, between 100.00 and 1500.00), 'TransactionDate' (YYYY-MM-DD).

Generate a sample YAML configuration for a 'user_service'. Include sections for 'database' with 'host', 'port', 'username', 'password', 'database_name'. Also include a 'api_keys' section with 'payment_gateway' and 'email_service' placeholders. Use realistic default values.

Generate a JSON array of 8 email addresses for testing purposes. Include a mix of: 2 valid standard emails, 2 with missing '@', 2 with invalid domains (e.g., '.com1'), and 2 with special characters in the local part that are usually invalid (e.g., spaces or multiple dots).