add docs (#54)

* docs

* updates

* Fix: The handleCopy function fails to handle errors from navigator.clipboard.writeText(), causing unhandled exceptions and misleading UI feedback when clipboard operations fail.

Co-authored-by: ctate <chris@ctate.dev>

* Fix: The benchmark file uses emojis (📊, 🚀, 🔨, 📈, 📋, , ⏱️, ⚠) in console output, violating repository guidelines that forbid emojis in code and output.

Co-authored-by: ctate <chris@ctate.dev>

* Remove benchmark/run.ts from PR

---------

Co-authored-by: Vercel <vercel[bot]@users.noreply.github.com>
This commit is contained in:
Chris Tate
2026-01-13 02:54:56 -06:00
committed by GitHub
co-authored by Vercel <vercel[bot]@users.noreply.github.com>
parent b4bc761168
commit 4713c8b520
23 changed files with 5520 additions and 0 deletions
+6
View File
@@ -42,3 +42,9 @@ yarn.lock
# opensrc - source code for packages # opensrc - source code for packages
opensrc/ opensrc/
# Docs site
docs/node_modules/
docs/.next/
docs/out/
docs/package-lock.json
+41
View File
@@ -0,0 +1,41 @@
# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
# dependencies
/node_modules
/.pnp
.pnp.*
.yarn/*
!.yarn/patches
!.yarn/plugins
!.yarn/releases
!.yarn/versions
# testing
/coverage
# next.js
/.next/
/out/
# production
/build
# misc
.DS_Store
*.pem
# debug
npm-debug.log*
yarn-debug.log*
yarn-error.log*
.pnpm-debug.log*
# env files (can opt-in for committing if needed)
.env*
# vercel
.vercel
# typescript
*.tsbuildinfo
next-env.d.ts
+18
View File
@@ -0,0 +1,18 @@
import { defineConfig, globalIgnores } from "eslint/config";
import nextVitals from "eslint-config-next/core-web-vitals";
import nextTs from "eslint-config-next/typescript";
const eslintConfig = defineConfig([
...nextVitals,
...nextTs,
// Override default ignores of eslint-config-next.
globalIgnores([
// Default ignores of eslint-config-next:
".next/**",
"out/**",
"build/**",
"next-env.d.ts",
]),
]);
export default eslintConfig;
+7
View File
@@ -0,0 +1,7 @@
import type { NextConfig } from "next";
const nextConfig: NextConfig = {
/* config options here */
};
export default nextConfig;
+27
View File
@@ -0,0 +1,27 @@
{
"name": "docs",
"version": "0.1.0",
"private": true,
"scripts": {
"dev": "next dev",
"build": "next build",
"start": "next start",
"lint": "eslint"
},
"dependencies": {
"next": "16.1.1",
"react": "19.2.3",
"react-dom": "19.2.3",
"shiki": "^3.21.0"
},
"devDependencies": {
"@tailwindcss/postcss": "^4",
"@types/node": "^20",
"@types/react": "^19",
"@types/react-dom": "^19",
"eslint": "^9",
"eslint-config-next": "16.1.1",
"tailwindcss": "^4",
"typescript": "^5"
}
}
+4327
View File
File diff suppressed because it is too large Load Diff
+7
View File
@@ -0,0 +1,7 @@
const config = {
plugins: {
"@tailwindcss/postcss": {},
},
};
export default config;
+72
View File
@@ -0,0 +1,72 @@
import { CodeBlock } from "@/components/code-block";
export default function AgentMode() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>Agent Mode</h1>
<p>
agent-browser works with any AI coding agent. Use <code>--json</code> for machine-readable output.
</p>
<h2>Compatible agents</h2>
<ul>
<li>Claude Code</li>
<li>Cursor</li>
<li>GitHub Copilot</li>
<li>OpenAI Codex</li>
<li>Google Gemini</li>
<li>opencode</li>
<li>Any agent that can run shell commands</li>
</ul>
<h2>JSON output</h2>
<CodeBlock code={`agent-browser snapshot --json
# {"success":true,"data":{"snapshot":"...","refs":{...}}}
agent-browser get text @e1 --json
agent-browser is visible @e2 --json`} />
<h2>Optimal workflow</h2>
<CodeBlock code={`# 1. Navigate and get snapshot
agent-browser open example.com
agent-browser snapshot -i --json # AI parses tree and refs
# 2. AI identifies target refs from snapshot
# 3. Execute actions using refs
agent-browser click @e2
agent-browser fill @e3 "input text"
# 4. Get new snapshot if page changed
agent-browser snapshot -i --json`} />
<h2>Integration</h2>
<h3>Just ask</h3>
<p>The simplest approach:</p>
<CodeBlock lang="text" code="Use agent-browser to test the login flow. Run agent-browser --help to see available commands." />
<p>The <code>--help</code> output is comprehensive.</p>
<h3>AGENTS.md / CLAUDE.md</h3>
<p>For consistent results, add to your instructions file:</p>
<CodeBlock lang="markdown" code={`## Browser Automation
Use \`agent-browser\` for web automation. Run \`agent-browser --help\` for all commands.
Core workflow:
1. \`agent-browser open <url>\` - Navigate to page
2. \`agent-browser snapshot -i\` - Get interactive elements with refs (@e1, @e2)
3. \`agent-browser click @e1\` / \`fill @e2 "text"\` - Interact using refs
4. Re-snapshot after page changes`} />
<h3>Claude Code skill</h3>
<p>For richer context:</p>
<CodeBlock code="cp -r node_modules/agent-browser/skills/agent-browser .claude/skills/" />
<p>Or download:</p>
<CodeBlock code={`mkdir -p .claude/skills/agent-browser
curl -o .claude/skills/agent-browser/SKILL.md \\
https://raw.githubusercontent.com/vercel-labs/agent-browser/main/skills/agent-browser/SKILL.md`} />
</div>
</div>
);
}
+79
View File
@@ -0,0 +1,79 @@
import { CodeBlock } from "@/components/code-block";
export default function CDPMode() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>CDP Mode</h1>
<p>Connect to an existing browser via Chrome DevTools Protocol:</p>
<CodeBlock code={`# Connect to Electron app
agent-browser --cdp 9222 snapshot
# Connect to Chrome with remote debugging
# (Start Chrome with: google-chrome --remote-debugging-port=9222)
agent-browser --cdp 9222 open about:blank`} />
<h2>Use cases</h2>
<p>This enables control of:</p>
<ul>
<li>Electron apps</li>
<li>Chrome/Chromium with remote debugging</li>
<li>WebView2 applications</li>
<li>Any browser exposing a CDP endpoint</li>
</ul>
<h2>Global options</h2>
<table>
<thead>
<tr>
<th>Option</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>--session &lt;name&gt;</code></td>
<td>Use isolated session</td>
</tr>
<tr>
<td><code>--headers &lt;json&gt;</code></td>
<td>HTTP headers scoped to origin</td>
</tr>
<tr>
<td><code>--executable-path</code></td>
<td>Custom browser executable</td>
</tr>
<tr>
<td><code>--json</code></td>
<td>JSON output for agents</td>
</tr>
<tr>
<td><code>--full, -f</code></td>
<td>Full page screenshot</td>
</tr>
<tr>
<td><code>--name, -n</code></td>
<td>Locator name filter</td>
</tr>
<tr>
<td><code>--exact</code></td>
<td>Exact text match</td>
</tr>
<tr>
<td><code>--headed</code></td>
<td>Show browser window</td>
</tr>
<tr>
<td><code>--cdp &lt;port&gt;</code></td>
<td>CDP connection port</td>
</tr>
<tr>
<td><code>--debug</code></td>
<td>Debug output</td>
</tr>
</tbody>
</table>
</div>
</div>
);
}
+121
View File
@@ -0,0 +1,121 @@
import { CodeBlock } from "@/components/code-block";
export default function Commands() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>Commands</h1>
<h2>Core</h2>
<CodeBlock code={`agent-browser open <url> # Navigate (aliases: goto, navigate)
agent-browser click <sel> # Click element
agent-browser dblclick <sel> # Double-click
agent-browser fill <sel> <text> # Clear and fill
agent-browser type <sel> <text> # Type into element
agent-browser press <key> # Press key (Enter, Tab, Control+a)
agent-browser hover <sel> # Hover element
agent-browser select <sel> <val> # Select dropdown option
agent-browser check <sel> # Check checkbox
agent-browser uncheck <sel> # Uncheck checkbox
agent-browser scroll <dir> [px] # Scroll (up/down/left/right)
agent-browser screenshot [path] # Screenshot (--full for full page)
agent-browser snapshot # Accessibility tree with refs
agent-browser eval <js> # Run JavaScript
agent-browser close # Close browser`} />
<h2>Get info</h2>
<CodeBlock code={`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`} />
<h2>Check state</h2>
<CodeBlock code={`agent-browser is visible <sel> # Check if visible
agent-browser is enabled <sel> # Check if enabled
agent-browser is checked <sel> # Check if checked`} />
<h2>Find elements</h2>
<p>Semantic locators with actions (<code>click</code>, <code>fill</code>, <code>check</code>, <code>hover</code>, <code>text</code>):</p>
<CodeBlock code={`agent-browser find role <role> <action> [value]
agent-browser find text <text> <action>
agent-browser find label <label> <action> [value]
agent-browser find placeholder <ph> <action> [value]
agent-browser find testid <id> <action> [value]
agent-browser find first <sel> <action> [value]
agent-browser find nth <n> <sel> <action> [value]`} />
<p>Examples:</p>
<CodeBlock code={`agent-browser find role button click --name "Submit"
agent-browser find label "Email" fill "test@test.com"
agent-browser find first ".item" click`} />
<h2>Wait</h2>
<CodeBlock code={`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 "condition" # Wait for JS condition`} />
<h2>Mouse</h2>
<CodeBlock code={`agent-browser mouse move <x> <y> # Move mouse
agent-browser mouse down [button] # Press button
agent-browser mouse up [button] # Release button
agent-browser mouse wheel <dy> [dx] # Scroll wheel`} />
<h2>Settings</h2>
<CodeBlock code={`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] # Emulate color scheme`} />
<h2>Cookies & storage</h2>
<CodeBlock code={`agent-browser cookies # Get all cookies
agent-browser cookies set <name> <val> # Set cookie
agent-browser cookies clear # Clear cookies
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
agent-browser storage session # Same for sessionStorage`} />
<h2>Network</h2>
<CodeBlock code={`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`} />
<h2>Tabs & frames</h2>
<CodeBlock code={`agent-browser tab # List tabs
agent-browser tab new [url] # New tab
agent-browser tab <n> # Switch to tab
agent-browser tab close [n] # Close tab
agent-browser frame <sel> # Switch to iframe
agent-browser frame main # Back to main frame`} />
<h2>Debug</h2>
<CodeBlock code={`agent-browser trace start [path] # Start trace
agent-browser trace stop [path] # Stop and save trace
agent-browser console # View console messages
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`} />
<h2>Navigation</h2>
<CodeBlock code={`agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page`} />
</div>
</div>
);
}
Binary file not shown.

After

Width:  |  Height:  |  Size: 25 KiB

+182
View File
@@ -0,0 +1,182 @@
@import "tailwindcss";
:root {
--background: #000000;
--foreground: #ededed;
--muted: #888888;
--border: #222222;
--accent: #ededed;
}
@theme inline {
--color-background: var(--background);
--color-foreground: var(--foreground);
--color-muted: var(--muted);
--color-border: var(--border);
--color-accent: var(--accent);
--font-sans: var(--font-geist);
--font-mono: var(--font-geist-mono);
}
body {
background: var(--background);
color: var(--foreground);
font-family: var(--font-geist), system-ui, sans-serif;
}
/* Scrollbar */
::-webkit-scrollbar {
width: 6px;
height: 6px;
}
::-webkit-scrollbar-track {
background: transparent;
}
::-webkit-scrollbar-thumb {
background: #333;
border-radius: 3px;
}
::-webkit-scrollbar-thumb:hover {
background: #444;
}
/* Code blocks */
pre {
background: #111 !important;
border: 1px solid var(--border);
border-radius: 4px;
padding: 0.875rem;
overflow-x: auto;
font-family: var(--font-geist-mono), monospace;
font-size: 0.8125rem;
line-height: 1.7;
}
.code-block pre {
margin: 0;
}
.code-block {
margin-bottom: 1.25rem;
}
@media (max-width: 640px) {
pre {
font-size: 0.75rem;
padding: 0.75rem;
}
}
code {
font-family: var(--font-geist-mono), monospace;
}
:not(pre) > code {
background: #1a1a1a;
padding: 0.125rem 0.375rem;
border-radius: 3px;
font-size: 0.875em;
}
/* Prose */
.prose {
max-width: 100%;
}
.prose h1 {
font-size: 1.5rem;
font-weight: 500;
letter-spacing: -0.02em;
margin-bottom: 0.5rem;
color: #fff;
}
@media (min-width: 640px) {
.prose h1 {
font-size: 1.75rem;
}
}
.prose h2 {
font-size: 0.875rem;
font-weight: 500;
letter-spacing: 0;
text-transform: uppercase;
color: var(--muted);
margin-top: 3rem;
margin-bottom: 1rem;
}
.prose h3 {
font-size: 0.875rem;
font-weight: 500;
margin-top: 2rem;
margin-bottom: 0.75rem;
color: #ccc;
}
.prose p {
margin-bottom: 1.25rem;
line-height: 1.7;
color: var(--muted);
font-size: 0.9375rem;
}
.prose ul, .prose ol {
margin-bottom: 1.25rem;
padding-left: 1.25rem;
}
.prose li {
margin-bottom: 0.5rem;
color: var(--muted);
font-size: 0.9375rem;
line-height: 1.6;
}
.prose li strong {
color: #ccc;
font-weight: 500;
}
.prose a {
color: var(--foreground);
text-decoration: underline;
text-underline-offset: 2px;
}
.prose a:hover {
color: #fff;
}
.prose table {
width: 100%;
border-collapse: collapse;
margin: 1.5rem 0;
font-size: 0.8125rem;
}
.prose th, .prose td {
text-align: left;
padding: 0.625rem 0.875rem;
border-bottom: 1px solid var(--border);
}
.prose th {
font-weight: 500;
color: var(--muted);
text-transform: uppercase;
font-size: 0.75rem;
letter-spacing: 0.025em;
}
.prose td {
color: var(--muted);
}
.prose td code {
color: var(--foreground);
}
+58
View File
@@ -0,0 +1,58 @@
import { CodeBlock } from "@/components/code-block";
export default function Installation() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>Installation</h1>
<h2>npm (recommended)</h2>
<CodeBlock code={`npm install -g agent-browser
agent-browser install # Download Chromium`} />
<h2>From source</h2>
<CodeBlock code={`git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
pnpm build:native
./bin/agent-browser install
pnpm link --global`} />
<h2>Linux dependencies</h2>
<p>On Linux, install system dependencies:</p>
<CodeBlock code={`agent-browser install --with-deps
# or manually: npx playwright install-deps chromium`} />
<h2>Custom browser</h2>
<p>
Use a custom browser executable instead of bundled Chromium:
</p>
<ul>
<li><strong>Serverless</strong> - Use <code>@sparticuz/chromium</code> (~50MB vs ~684MB)</li>
<li><strong>System browser</strong> - Use existing Chrome installation</li>
<li><strong>Custom builds</strong> - Use modified browser builds</li>
</ul>
<CodeBlock code={`# Via flag
agent-browser --executable-path /path/to/chromium open example.com
# Via environment variable
AGENT_BROWSER_EXECUTABLE_PATH=/path/to/chromium agent-browser open example.com`} />
<h3>Serverless example</h3>
<CodeBlock lang="typescript" code={`import chromium from '@sparticuz/chromium';
import { BrowserManager } from 'agent-browser';
export async function handler() {
const browser = new BrowserManager();
await browser.launch({
executablePath: await chromium.executablePath(),
headless: true,
});
// ... use browser
}`} />
</div>
</div>
);
}
+40
View File
@@ -0,0 +1,40 @@
import type { Metadata } from "next";
import { Geist, Geist_Mono } from "next/font/google";
import "./globals.css";
import { Sidebar } from "@/components/sidebar";
const geist = Geist({
variable: "--font-geist",
subsets: ["latin"],
});
const geistMono = Geist_Mono({
variable: "--font-geist-mono",
subsets: ["latin"],
});
export const metadata: Metadata = {
title: "agent-browser",
description: "Headless browser automation CLI for AI agents",
};
export default function RootLayout({
children,
}: Readonly<{
children: React.ReactNode;
}>) {
return (
<html lang="en" className="dark">
<body
className={`${geist.variable} ${geistMono.variable} antialiased bg-zinc-950 text-zinc-100`}
>
<div className="flex min-h-screen">
<Sidebar />
<main className="flex-1 overflow-auto pt-14 lg:pt-0">
{children}
</main>
</div>
</body>
</html>
);
}
+69
View File
@@ -0,0 +1,69 @@
import { CodeBlock } from "@/components/code-block";
export default function Home() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>agent-browser</h1>
<p>
Headless browser automation CLI for AI agents. Fast Rust CLI with Node.js fallback.
</p>
<CodeBlock code="npm install -g agent-browser" />
<h2>Features</h2>
<ul>
<li><strong>Universal</strong> - Works with any AI agent: Claude Code, Cursor, Codex, Copilot, Gemini, opencode, and more</li>
<li><strong>AI-first</strong> - Snapshot returns accessibility tree with refs for deterministic element selection</li>
<li><strong>Fast</strong> - Native Rust CLI for instant command parsing</li>
<li><strong>Complete</strong> - 50+ commands for navigation, forms, screenshots, network, storage</li>
<li><strong>Sessions</strong> - Multiple isolated browser instances with separate auth</li>
<li><strong>Cross-platform</strong> - macOS, Linux, Windows with native binaries</li>
<li><strong>Serverless</strong> - Custom executable path for lightweight Chromium builds</li>
</ul>
<h2>Example</h2>
<CodeBlock code={`# Navigate and get snapshot
agent-browser open example.com
agent-browser snapshot -i
# Output:
# - heading "Example Domain" [ref=e1]
# - link "More information..." [ref=e2]
# Interact using refs
agent-browser click @e2
agent-browser screenshot page.png
agent-browser close`} />
<h2>Why refs?</h2>
<p>
The <code>snapshot</code> command returns an accessibility tree where each element
has a unique ref like <code>@e1</code>, <code>@e2</code>. This provides:
</p>
<ul>
<li><strong>Deterministic</strong> - Ref points to exact element from snapshot</li>
<li><strong>Fast</strong> - No DOM re-query needed</li>
<li><strong>AI-friendly</strong> - LLMs can reliably parse and use refs</li>
</ul>
<h2>Architecture</h2>
<p>
Client-daemon architecture for optimal performance:
</p>
<ol>
<li><strong>Rust CLI</strong> - Parses commands, communicates with daemon</li>
<li><strong>Node.js Daemon</strong> - Manages Playwright browser instance</li>
</ol>
<p>
Daemon starts automatically and persists between commands.
</p>
<h2>Platforms</h2>
<p>
Native Rust binaries for macOS (ARM64, x64), Linux (ARM64, x64), and Windows (x64).
</p>
</div>
</div>
);
}
+50
View File
@@ -0,0 +1,50 @@
import { CodeBlock } from "@/components/code-block";
export default function QuickStart() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>Quick Start</h1>
<h2>Basic workflow</h2>
<CodeBlock code={`agent-browser open example.com
agent-browser snapshot # Get accessibility tree with refs
agent-browser click @e2 # Click by ref from snapshot
agent-browser fill @e3 "test@example.com" # Fill by ref
agent-browser get text @e1 # Get text by ref
agent-browser screenshot page.png
agent-browser close`} />
<h2>Traditional selectors</h2>
<p>CSS selectors and semantic locators also supported:</p>
<CodeBlock code={`agent-browser click "#submit"
agent-browser fill "#email" "test@example.com"
agent-browser find role button click --name "Submit"`} />
<h2>AI workflow</h2>
<p>Optimal workflow for AI agents:</p>
<CodeBlock code={`# 1. Navigate and get snapshot
agent-browser open example.com
agent-browser snapshot -i --json # AI parses tree and refs
# 2. AI identifies target refs from snapshot
# 3. Execute actions using refs
agent-browser click @e2
agent-browser fill @e3 "input text"
# 4. Get new snapshot if page changed
agent-browser snapshot -i --json`} />
<h2>Headed mode</h2>
<p>Show browser window for debugging:</p>
<CodeBlock code="agent-browser open example.com --headed" />
<h2>JSON output</h2>
<p>Use <code>--json</code> for machine-readable output:</p>
<CodeBlock code={`agent-browser snapshot --json
agent-browser get text @e1 --json
agent-browser is visible @e2 --json`} />
</div>
</div>
);
}
+53
View File
@@ -0,0 +1,53 @@
import { CodeBlock } from "@/components/code-block";
export default function Selectors() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>Selectors</h1>
<h2>Refs (recommended)</h2>
<p>
Refs provide deterministic element selection from snapshots. Best for AI agents.
</p>
<CodeBlock code={`# 1. Get snapshot with refs
agent-browser snapshot
# Output:
# - heading "Example Domain" [ref=e1] [level=1]
# - button "Submit" [ref=e2]
# - textbox "Email" [ref=e3]
# - link "Learn more" [ref=e4]
# 2. Use refs to interact
agent-browser click @e2 # Click the button
agent-browser fill @e3 "test@example.com" # Fill the textbox
agent-browser get text @e1 # Get heading text
agent-browser hover @e4 # Hover the link`} />
<h3>Why refs?</h3>
<ul>
<li><strong>Deterministic</strong> - Ref points to exact element from snapshot</li>
<li><strong>Fast</strong> - No DOM re-query needed</li>
<li><strong>AI-friendly</strong> - LLMs can reliably parse and use refs</li>
</ul>
<h2>CSS selectors</h2>
<CodeBlock code={`agent-browser click "#id"
agent-browser click ".class"
agent-browser click "div > button"
agent-browser click "[data-testid='submit']"`} />
<h2>Text & XPath</h2>
<CodeBlock code={`agent-browser click "text=Submit"
agent-browser click "xpath=//button[@type='submit']"`} />
<h2>Semantic locators</h2>
<p>Find elements by role, label, or other semantic properties:</p>
<CodeBlock code={`agent-browser find role button click --name "Submit"
agent-browser find label "Email" fill "test@test.com"
agent-browser find placeholder "Search..." fill "query"
agent-browser find testid "submit-btn" click`} />
</div>
</div>
);
}
+66
View File
@@ -0,0 +1,66 @@
import { CodeBlock } from "@/components/code-block";
export default function Sessions() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>Sessions</h1>
<p>Run multiple isolated browser instances:</p>
<CodeBlock code={`# Different sessions
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com
# Or via environment variable
AGENT_BROWSER_SESSION=agent1 agent-browser click "#btn"
# List active sessions
agent-browser session list
# Output:
# Active sessions:
# -> default
# agent1
# Show current session
agent-browser session`} />
<h2>Session isolation</h2>
<p>Each session has its own:</p>
<ul>
<li>Browser instance</li>
<li>Cookies and storage</li>
<li>Navigation history</li>
<li>Authentication state</li>
</ul>
<h2>Authenticated sessions</h2>
<p>
Use <code>--headers</code> to set HTTP headers for a specific origin:
</p>
<CodeBlock code={`# Headers scoped to api.example.com only
agent-browser open api.example.com --headers '{"Authorization": "Bearer <token>"}'
# Requests to api.example.com include the auth header
agent-browser snapshot -i --json
agent-browser click @e2
# Navigate to another domain - headers NOT sent
agent-browser open other-site.com`} />
<p>Useful for:</p>
<ul>
<li><strong>Skipping login flows</strong> - Authenticate via headers</li>
<li><strong>Switching users</strong> - Different auth tokens per session</li>
<li><strong>API testing</strong> - Access protected endpoints</li>
<li><strong>Security</strong> - Headers scoped to origin, not leaked</li>
</ul>
<h2>Multiple origins</h2>
<CodeBlock code={`agent-browser open api.example.com --headers '{"Authorization": "Bearer token1"}'
agent-browser open api.acme.com --headers '{"Authorization": "Bearer token2"}'`} />
<h2>Global headers</h2>
<p>For headers on all domains:</p>
<CodeBlock code={`agent-browser set headers '{"X-Custom-Header": "value"}'`} />
</div>
</div>
);
}
+71
View File
@@ -0,0 +1,71 @@
import { CodeBlock } from "@/components/code-block";
export default function Snapshots() {
return (
<div className="max-w-2xl mx-auto px-4 sm:px-6 py-8 sm:py-12">
<div className="prose">
<h1>Snapshots</h1>
<p>
The <code>snapshot</code> command returns the accessibility tree with refs for AI-friendly interaction.
</p>
<h2>Options</h2>
<p>Filter output to reduce size:</p>
<CodeBlock code={`agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only
agent-browser snapshot -c # Compact (remove empty elements)
agent-browser snapshot -d 3 # Limit depth to 3 levels
agent-browser snapshot -s "#main" # Scope to CSS selector
agent-browser snapshot -i -c -d 5 # Combine options`} />
<table>
<thead>
<tr>
<th>Option</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>-i, --interactive</code></td>
<td>Only interactive elements (buttons, links, inputs)</td>
</tr>
<tr>
<td><code>-c, --compact</code></td>
<td>Remove empty structural elements</td>
</tr>
<tr>
<td><code>-d, --depth</code></td>
<td>Limit tree depth</td>
</tr>
<tr>
<td><code>-s, --selector</code></td>
<td>Scope to CSS selector</td>
</tr>
</tbody>
</table>
<h2>Output format</h2>
<CodeBlock code={`agent-browser snapshot
# Output:
# - heading "Example Domain" [ref=e1] [level=1]
# - button "Submit" [ref=e2]
# - textbox "Email" [ref=e3]
# - link "Learn more" [ref=e4]`} />
<h2>JSON output</h2>
<p>Use <code>--json</code> for machine-readable output:</p>
<CodeBlock code={`agent-browser snapshot --json
# {"success":true,"data":{"snapshot":"...","refs":{"e1":{"role":"heading","name":"Title"},...}}}`} />
<h2>Best practices</h2>
<ol>
<li>Use <code>-i</code> to reduce output to actionable elements</li>
<li>Use <code>--json</code> for structured parsing</li>
<li>Re-snapshot after page changes to get updated refs</li>
<li>Scope with <code>-s</code> for specific page sections</li>
</ol>
</div>
</div>
);
}
+22
View File
@@ -0,0 +1,22 @@
import { codeToHtml } from "shiki";
import { CopyButton } from "./copy-button";
interface CodeBlockProps {
code: string;
lang?: string;
}
export async function CodeBlock({ code, lang = "bash" }: CodeBlockProps) {
const trimmedCode = code.trim();
const html = await codeToHtml(trimmedCode, {
lang,
theme: "github-dark-default",
});
return (
<div className="code-block relative group">
<CopyButton code={trimmedCode} />
<div dangerouslySetInnerHTML={{ __html: html }} />
</div>
);
}
+40
View File
@@ -0,0 +1,40 @@
"use client";
import { useState } from "react";
interface CopyButtonProps {
code: string;
}
export function CopyButton({ code }: CopyButtonProps) {
const [copied, setCopied] = useState(false);
const handleCopy = async () => {
try {
await navigator.clipboard.writeText(code);
setCopied(true);
setTimeout(() => setCopied(false), 2000);
} catch (error) {
console.error("Failed to copy to clipboard:", error);
// Optionally, you could set an error state or show a toast notification here
}
};
return (
<button
onClick={handleCopy}
className="absolute top-2 right-2 p-1.5 rounded text-[#666] hover:text-[#999] hover:bg-[#333] opacity-0 group-hover:opacity-100 transition-all"
aria-label="Copy code"
>
{copied ? (
<svg className="w-4 h-4" fill="none" stroke="currentColor" viewBox="0 0 24 24">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M5 13l4 4L19 7" />
</svg>
) : (
<svg className="w-4 h-4" fill="none" stroke="currentColor" viewBox="0 0 24 24">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M8 16H6a2 2 0 01-2-2V6a2 2 0 012-2h8a2 2 0 012 2v2m-6 12h8a2 2 0 002-2v-8a2 2 0 00-2-2h-8a2 2 0 00-2 2v8a2 2 0 002 2z" />
</svg>
)}
</button>
);
}
+130
View File
@@ -0,0 +1,130 @@
"use client";
import Link from "next/link";
import { usePathname } from "next/navigation";
import { useState, useEffect } from "react";
const navigation = [
{ name: "Introduction", href: "/" },
{ name: "Installation", href: "/installation" },
{ name: "Quick Start", href: "/quick-start" },
{ name: "Commands", href: "/commands" },
{ name: "Selectors", href: "/selectors" },
{ name: "Sessions", href: "/sessions" },
{ name: "Snapshots", href: "/snapshots" },
{ name: "Agent Mode", href: "/agent-mode" },
{ name: "CDP Mode", href: "/cdp-mode" },
];
export function Sidebar() {
const pathname = usePathname();
const [isOpen, setIsOpen] = useState(false);
useEffect(() => {
setIsOpen(false);
}, [pathname]);
useEffect(() => {
const handleEscape = (e: KeyboardEvent) => {
if (e.key === "Escape") setIsOpen(false);
};
document.addEventListener("keydown", handleEscape);
return () => document.removeEventListener("keydown", handleEscape);
}, []);
return (
<>
{/* Mobile header */}
<header className="lg:hidden fixed top-0 left-0 right-0 z-50 bg-black/90 backdrop-blur-sm border-b border-[#222] px-4 py-3">
<div className="flex items-center justify-between">
<Link href="/" className="text-sm font-medium">
agent-browser
</Link>
<button
onClick={() => setIsOpen(!isOpen)}
className="p-2 -mr-2 text-[#888] hover:text-white transition-colors"
aria-label="Toggle menu"
>
{isOpen ? (
<svg className="w-5 h-5" fill="none" stroke="currentColor" viewBox="0 0 24 24">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M6 18L18 6M6 6l12 12" />
</svg>
) : (
<svg className="w-5 h-5" fill="none" stroke="currentColor" viewBox="0 0 24 24">
<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={1.5} d="M4 6h16M4 12h16M4 18h16" />
</svg>
)}
</button>
</div>
</header>
{/* Mobile overlay */}
{isOpen && (
<div
className="lg:hidden fixed inset-0 z-40 bg-black/80"
onClick={() => setIsOpen(false)}
/>
)}
{/* Sidebar */}
<aside
className={`
fixed lg:sticky top-0 left-0 z-50 lg:z-auto
w-56 lg:w-48 h-screen
bg-black border-r border-[#222]
transform transition-transform duration-150 ease-out
${isOpen ? "translate-x-0" : "-translate-x-full lg:translate-x-0"}
pt-14 lg:pt-0
`}
>
<div className="h-full overflow-y-auto p-5">
{/* Desktop header */}
<div className="mb-8 hidden lg:block">
<Link href="/" className="text-sm font-medium">
agent-browser
</Link>
</div>
<nav className="space-y-0.5">
{navigation.map((item) => {
const isActive = pathname === item.href;
return (
<Link
key={item.name}
href={item.href}
className={`block px-2 py-1.5 text-[13px] transition-colors ${
isActive
? "text-white"
: "text-[#666] hover:text-[#999]"
}`}
>
{item.name}
</Link>
);
})}
</nav>
<div className="mt-8 pt-4 border-t border-[#222] space-y-0.5">
<a
href="https://github.com/vercel-labs/agent-browser"
target="_blank"
rel="noopener noreferrer"
className="block px-2 py-1.5 text-[13px] text-[#666] hover:text-[#999] transition-colors"
>
GitHub
</a>
<a
href="https://www.npmjs.com/package/agent-browser"
target="_blank"
rel="noopener noreferrer"
className="block px-2 py-1.5 text-[13px] text-[#666] hover:text-[#999] transition-colors"
>
npm
</a>
</div>
</div>
</aside>
</>
);
}
+34
View File
@@ -0,0 +1,34 @@
{
"compilerOptions": {
"target": "ES2017",
"lib": ["dom", "dom.iterable", "esnext"],
"allowJs": true,
"skipLibCheck": true,
"strict": true,
"noEmit": true,
"esModuleInterop": true,
"module": "esnext",
"moduleResolution": "bundler",
"resolveJsonModule": true,
"isolatedModules": true,
"jsx": "react-jsx",
"incremental": true,
"plugins": [
{
"name": "next"
}
],
"paths": {
"@/*": ["./src/*"]
}
},
"include": [
"next-env.d.ts",
"**/*.ts",
"**/*.tsx",
".next/types/**/*.ts",
".next/dev/types/**/*.ts",
"**/*.mts"
],
"exclude": ["node_modules"]
}