agent-browser

This commit is contained in:
Chris Tate
2026-01-10 22:51:59 -06:00
parent 6de8102978
commit 0cd29aa119
6 changed files with 194 additions and 194 deletions
+127 -127
View File
@@ -1,6 +1,6 @@
# veb
# agent-browser
Headless browser automation CLI for agents and humans.
Headless browser automation CLI for AI agents.
## Installation
@@ -13,12 +13,12 @@ pnpm build
## Quick Start
```bash
veb open example.com
veb click "#submit"
veb fill "#email" "test@example.com"
veb get text "h1"
veb screenshot page.png
veb close
agent-browser open example.com
agent-browser click "#submit"
agent-browser fill "#email" "test@example.com"
agent-browser get text "h1"
agent-browser screenshot page.png
agent-browser close
```
## Commands
@@ -26,87 +26,87 @@ veb close
### Core Commands
```bash
veb open <url> # Navigate to URL
veb click <sel> # Click element
veb type <sel> <text> # Type into element
veb fill <sel> <text> # Clear and fill
veb press <key> # Press key (Enter, Tab, Control+a)
veb keydown <key> # Hold key down
veb keyup <key> # Release key
veb insert <text> # Insert text (no key events)
veb hover <sel> # Hover element
veb select <sel> <val> # Select dropdown option
veb multiselect <sel> <v1> <v2> # Multi-select
veb check <sel> # Check checkbox
veb uncheck <sel> # Uncheck checkbox
veb scroll <dir> [px] # Scroll (up/down/left/right)
veb scrollinto <sel> # Scroll element into view
veb drag <src> <tgt> # Drag and drop
veb upload <sel> <files> # Upload files
veb download [path] # Wait for download
veb screenshot [path] # Take screenshot (--full for full page)
veb pdf <path> # Save as PDF
veb snapshot # Accessibility tree (best for AI)
veb eval <js> # Run JavaScript
veb close # Close browser
agent-browser open <url> # Navigate to URL
agent-browser click <sel> # Click element
agent-browser type <sel> <text> # Type into element
agent-browser fill <sel> <text> # Clear and fill
agent-browser press <key> # Press key (Enter, Tab, Control+a)
agent-browser keydown <key> # Hold key down
agent-browser keyup <key> # Release key
agent-browser insert <text> # Insert text (no key events)
agent-browser hover <sel> # Hover element
agent-browser select <sel> <val> # Select dropdown option
agent-browser multiselect <sel> <v1> <v2> # Multi-select
agent-browser check <sel> # Check checkbox
agent-browser uncheck <sel> # Uncheck checkbox
agent-browser scroll <dir> [px] # Scroll (up/down/left/right)
agent-browser scrollinto <sel> # Scroll element into view
agent-browser drag <src> <tgt> # Drag and drop
agent-browser upload <sel> <files> # Upload files
agent-browser download [path] # Wait for download
agent-browser screenshot [path] # Take screenshot (--full for full page)
agent-browser pdf <path> # Save as PDF
agent-browser snapshot # Accessibility tree (best for AI)
agent-browser eval <js> # Run JavaScript
agent-browser close # Close browser
```
### Get Info
```bash
veb get text <sel> # Get text content
veb get html <sel> # Get innerHTML
veb get value <sel> # Get input value
veb get attr <sel> <attr> # Get attribute
veb get title # Get page title
veb get url # Get current URL
veb get count <sel> # Count matching elements
veb get box <sel> # Get bounding box
agent-browser get text <sel> # Get text content
agent-browser get html <sel> # Get innerHTML
agent-browser get value <sel> # Get input value
agent-browser get attr <sel> <attr> # Get attribute
agent-browser get title # Get page title
agent-browser get url # Get current URL
agent-browser get count <sel> # Count matching elements
agent-browser get box <sel> # Get bounding box
```
### Check State
```bash
veb is visible <sel> # Check if visible
veb is enabled <sel> # Check if enabled
veb is checked <sel> # Check if checked
agent-browser is visible <sel> # Check if visible
agent-browser is enabled <sel> # Check if enabled
agent-browser is checked <sel> # Check if checked
```
### Find Elements (Semantic Locators)
```bash
veb find role <role> <action> [value] # By ARIA role
veb find text <text> <action> # By text content
veb find label <label> <action> [value] # By label
veb find placeholder <ph> <action> [value] # By placeholder
veb find alt <text> <action> # By alt text
veb find title <text> <action> # By title attr
veb find testid <id> <action> [value] # By data-testid
veb find first <sel> <action> [value] # First match
veb find last <sel> <action> [value] # Last match
veb find nth <n> <sel> <action> [value] # Nth match
agent-browser find role <role> <action> [value] # By ARIA role
agent-browser find text <text> <action> # By text content
agent-browser find label <label> <action> [value] # By label
agent-browser find placeholder <ph> <action> [value] # By placeholder
agent-browser find alt <text> <action> # By alt text
agent-browser find title <text> <action> # By title attr
agent-browser find testid <id> <action> [value] # By data-testid
agent-browser find first <sel> <action> [value] # First match
agent-browser find last <sel> <action> [value] # Last match
agent-browser find nth <n> <sel> <action> [value] # Nth match
```
**Actions:** `click`, `fill`, `check`, `hover`, `text`
**Examples:**
```bash
veb find role button click --name "Submit"
veb find text "Sign In" click
veb find label "Email" fill "test@test.com"
veb find first ".item" click
veb find nth 2 "a" text
agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "test@test.com"
agent-browser find first ".item" click
agent-browser find nth 2 "a" text
```
### Wait
```bash
veb wait <selector> # Wait for element
veb wait <ms> # Wait for time
veb wait --text "Welcome" # Wait for text
veb wait --url "**/dash" # Wait for URL pattern
veb wait --load networkidle # Wait for load state
veb wait --fn "window.ready === true" # Wait for JS condition
agent-browser wait <selector> # Wait for element
agent-browser wait <ms> # Wait for time
agent-browser wait --text "Welcome" # Wait for text
agent-browser wait --url "**/dash" # Wait for URL pattern
agent-browser wait --load networkidle # Wait for load state
agent-browser wait --fn "window.ready === true" # Wait for JS condition
```
**Load states:** `load`, `domcontentloaded`, `networkidle`
@@ -114,109 +114,109 @@ veb wait --fn "window.ready === true" # Wait for JS condition
### Mouse Control
```bash
veb mouse move <x> <y> # Move mouse
veb mouse down [button] # Press button (left/right/middle)
veb mouse up [button] # Release button
veb mouse wheel <dy> [dx] # Scroll wheel
agent-browser mouse move <x> <y> # Move mouse
agent-browser mouse down [button] # Press button (left/right/middle)
agent-browser mouse up [button] # Release button
agent-browser mouse wheel <dy> [dx] # Scroll wheel
```
### Browser Settings
```bash
veb set viewport <w> <h> # Set viewport size
veb set device <name> # Emulate device ("iPhone 14")
veb set geo <lat> <lng> # Set geolocation
veb set offline [on|off] # Toggle offline mode
veb set headers <json> # Extra HTTP headers
veb set credentials <u> <p> # HTTP basic auth
veb set media [dark|light|print] # Emulate media
agent-browser set viewport <w> <h> # Set viewport size
agent-browser set device <name> # Emulate device ("iPhone 14")
agent-browser set geo <lat> <lng> # Set geolocation
agent-browser set offline [on|off] # Toggle offline mode
agent-browser set headers <json> # Extra HTTP headers
agent-browser set credentials <u> <p> # HTTP basic auth
agent-browser set media [dark|light|print] # Emulate media
```
### Cookies & Storage
```bash
veb cookies # Get all cookies
veb cookies set <json> # Set cookies
veb cookies clear # Clear cookies
agent-browser cookies # Get all cookies
agent-browser cookies set <json> # Set cookies
agent-browser cookies clear # Clear cookies
veb storage local # Get all localStorage
veb storage local <key> # Get specific key
veb storage local set <k> <v> # Set value
veb storage local clear # Clear all
agent-browser storage local # Get all localStorage
agent-browser storage local <key> # Get specific key
agent-browser storage local set <k> <v> # Set value
agent-browser storage local clear # Clear all
veb storage session # Same for sessionStorage
agent-browser storage session # Same for sessionStorage
```
### Network
```bash
veb network route <url> # Intercept requests
veb network route <url> --abort # Block requests
veb network route <url> --body <json> # Mock response
veb network unroute [url] # Remove routes
veb network requests # View tracked requests
veb network requests --filter api # Filter requests
veb response <url> # Get response body (waits for matching request)
agent-browser network route <url> # Intercept requests
agent-browser network route <url> --abort # Block requests
agent-browser network route <url> --body <json> # Mock response
agent-browser network unroute [url] # Remove routes
agent-browser network requests # View tracked requests
agent-browser network requests --filter api # Filter requests
agent-browser response <url> # Get response body (waits for matching request)
```
### Tabs & Windows
```bash
veb tab # List tabs
veb tab new # New tab
veb tab <n> # Switch to tab n
veb tab close [n] # Close tab
veb window new # New window
agent-browser tab # List tabs
agent-browser tab new # New tab
agent-browser tab <n> # Switch to tab n
agent-browser tab close [n] # Close tab
agent-browser window new # New window
```
### Frames
```bash
veb frame <sel> # Switch to iframe
veb frame main # Back to main frame
agent-browser frame <sel> # Switch to iframe
agent-browser frame main # Back to main frame
```
### Dialogs
```bash
veb dialog accept [text] # Accept (with optional prompt text)
veb dialog dismiss # Dismiss
agent-browser dialog accept [text] # Accept (with optional prompt text)
agent-browser dialog dismiss # Dismiss
```
### Debug
```bash
veb trace start # Start recording trace
veb trace stop <path> # Stop and save trace
veb console # View console messages
veb console --clear # Clear console
veb errors # View page errors
veb highlight <sel> # Highlight element
veb state save <path> # Save auth state
veb state load <path> # Load auth state
veb initscript <js> # Run JS on every page load
agent-browser trace start # Start recording trace
agent-browser trace stop <path> # Stop and save trace
agent-browser console # View console messages
agent-browser console --clear # Clear console
agent-browser errors # View page errors
agent-browser highlight <sel> # Highlight element
agent-browser state save <path> # Save auth state
agent-browser state load <path> # Load auth state
agent-browser initscript <js> # Run JS on every page load
```
### Navigation
```bash
veb back # Go back
veb forward # Go forward
veb reload # Reload page
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
```
### Sessions
```bash
veb session # Show current session
veb session list # List active sessions
agent-browser session # Show current session
agent-browser session list # List active sessions
```
## Options
| Option | Description |
|--------|-------------|
| `--session <name>` | Use isolated session (or `VEB_SESSION` env) |
| `--session <name>` | Use isolated session (or `AGENT_BROWSER_SESSION` env) |
| `--json` | JSON output (for agents) |
| `--full, -f` | Full page screenshot |
| `--name, -n` | Locator name filter |
@@ -229,33 +229,33 @@ Run multiple isolated browser instances:
```bash
# Different sessions
veb --session agent1 open site-a.com
veb --session agent2 open site-b.com
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com
# Or via environment
VEB_SESSION=agent1 veb click "#btn"
AGENT_BROWSER_SESSION=agent1 agent-browser click "#btn"
# List all
veb session list
agent-browser session list
```
## Selectors
```bash
# CSS
veb click "#id"
veb click ".class"
veb click "div > button"
agent-browser click "#id"
agent-browser click ".class"
agent-browser click "div > button"
# Text
veb click "text=Submit"
agent-browser click "text=Submit"
# XPath
veb click "xpath=//button"
agent-browser click "xpath=//button"
# Semantic (recommended)
veb find role button click --name "Submit"
veb find label "Email" fill "test@test.com"
agent-browser find role button click --name "Submit"
agent-browser find label "Email" fill "test@test.com"
```
## Agent Mode
@@ -263,9 +263,9 @@ veb find label "Email" fill "test@test.com"
Use `--json` for machine-readable output:
```bash
veb snapshot --json
veb get text "h1" --json
veb is visible ".modal" --json
agent-browser snapshot --json
agent-browser get text "h1" --json
agent-browser is visible ".modal" --json
```
## License