Automates Brave Browser as the primary engine using the Chrome DevTools Protocol, providing capabilities for navigation, element interaction (click, type, fill), screenshots, PDF generation, network interception and monitoring, console debugging, accessibility tree inspection, and device emulation.
Automates Google Chrome (and Chromium) as fallback browsers using the Chrome DevTools Protocol, providing capabilities for navigation, element interaction, screenshots, network monitoring, console debugging, and session management.
cdpilot
Zero-dependency browser automation from your terminal. One command, full control.
Quick Start
npx cdpilot launch # Start browser with CDP
npx cdpilot go https://example.com
npx cdpilot shot # Take screenshotNo config files. No boilerplate. Just npx and go.
Why cdpilot?
AI agents and developers need browser control that just works:
Zero config —
npx cdpilot launchstarts an isolated browser sessionZero dependency — No Puppeteer, no Playwright, no Selenium. Pure CDP over HTTP
40+ commands — Navigate, click, type, screenshot, network, console, accessibility, and more
AI-agent friendly — Designed for Claude, GPT, Gemini, and any LLM tool-use workflow
Isolated sessions — Your personal browser stays untouched. cdpilot runs in its own profile
Visual feedback — Green glow overlay, cursor visualization, click ripples, and keystroke display keep you informed during automation
Multi-project isolation — Each project gets its own browser instance and port automatically, no conflicts
AI control warning — Red toast notification appears when you hover during active automation
Privacy-first — Everything runs locally. No data leaves your machine
Why Brave?
cdpilot uses Brave Browser as its engine. Here's why:
Feature | Brave | Chrome | Why it matters |
Built-in ad blocker | Shields (native) | Extension needed | Pages load faster, less noise in DOM |
Tracker blocking | Default on | Manual config | Cleaner network logs for debugging |
Fingerprint protection | Native | None | Better privacy for automated sessions |
Chromium-based | Full CDP support | Full CDP support | Same DevTools Protocol, same power |
Open source | Yes (MPL 2.0) | Chromium yes, Chrome no | Transparent, auditable |
Resource usage | Lower memory | Higher memory | Better for running alongside your work |
TL;DR: Brave = Chrome's power + built-in privacy + less bloat. Perfect for automation.
cdpilot also works with Chrome and Chromium as fallback. Brave is recommended, not required.
Installation
# Use directly (no install needed)
npx cdpilot <command>
# Or install globally
npm i -g cdpilotRequirements: Node.js 18+ and one of: Brave Browser, Google Chrome, or Chromium.
First-time setup
npx cdpilot setup # Auto-detect browser, create isolated profile
npx cdpilot launch # Start browser with CDP enabled
npx cdpilot status # Check connectionCommands
Navigation & Content
cdpilot go <url> # Navigate to URL
cdpilot content # Get page text content
cdpilot html # Get page HTML
cdpilot shot [file] # Take screenshot (PNG)
cdpilot pdf [file] # Save page as PDFInteraction
cdpilot click <selector> # Click element
cdpilot type <selector> <text># Type into input
cdpilot fill <selector> <val> # Set input value (React-compatible)
cdpilot submit <form> # Submit form
cdpilot hover <selector> # Hover element
cdpilot keys <combo> # Keyboard shortcut (ctrl+a, enter, etc.)
cdpilot scroll-to <selector> # Scroll element into view
cdpilot drag <from> <to> # Drag and dropDebugging
cdpilot console [url] # Capture console logs
cdpilot network [url] # Monitor network requests
cdpilot debug [url] # Full diagnostic (console+network+perf+shot)
cdpilot perf # Performance metrics
cdpilot eval <js> # Execute JavaScriptTab Management
cdpilot tabs # List open tabs
cdpilot new-tab [url] # Open new tab
cdpilot switch-tab <id> # Switch to tab
cdpilot close-tab [id] # Close tab
cdpilot close # Close active tabNetwork Control
cdpilot throttle slow3g # Simulate slow 3G
cdpilot throttle fast3g # Simulate fast 3G
cdpilot throttle offline # Go offline
cdpilot throttle off # Back to normal
cdpilot proxy <url> # Set proxy
cdpilot proxy off # Remove proxyRequest Interception
cdpilot intercept block <pattern> # Block requests
cdpilot intercept mock <pattern> <json-file> # Mock responses
cdpilot intercept headers <pattern> <header:value> # Add headers
cdpilot intercept list # List active rules
cdpilot intercept clear # Clear all rulesDevice Emulation
cdpilot emulate iphone # iPhone emulation
cdpilot emulate ipad # iPad emulation
cdpilot emulate android # Android emulation
cdpilot emulate reset # Back to desktopGeolocation
cdpilot geo istanbul # Set location to Istanbul
cdpilot geo london # Set location to London
cdpilot geo 41.01 28.97 # Custom coordinates
cdpilot geo off # Remove overrideAccessibility
cdpilot a11y # Full accessibility tree
cdpilot a11y summary # Quick summary
cdpilot a11y find <role> # Find elements by ARIA roleSession Management
cdpilot session # Current session info
cdpilot sessions # List all sessions
cdpilot session-close [id] # Close sessionAdvanced
cdpilot cookies [domain] # List cookies
cdpilot storage # localStorage contents
cdpilot upload <sel> <file> # Upload file to input
cdpilot multi-eval <js> # Execute JS in all tabs
cdpilot headless [on|off] # Toggle headless mode
cdpilot frame list # List iframes
cdpilot dialog auto-accept # Auto-accept dialogs
cdpilot permission grant geo # Grant geolocationUse with AI Agents
cdpilot is designed to be called by AI agents as a tool:
Claude Code (MCP)
{
"mcpServers": {
"cdpilot": {
"command": "npx",
"args": ["cdpilot", "mcp"]
}
}
}Any LLM (tool-use)
{
"name": "browser",
"description": "Control a browser via CDP",
"parameters": {
"command": "go https://example.com"
}
}Python (subprocess)
import subprocess
result = subprocess.run(["npx", "cdpilot", "go", url], capture_output=True, text=True)
print(result.stdout)Environment Variables
Variable | Default | Description |
|
| CDP debugging port |
| Auto-detect | Browser binary path |
|
| Isolated browser profile |
| Auto | Session identifier |
How It Works
┌─────────────┐ HTTP/WebSocket ┌──────────────┐
│ cdpilot │ ◄──────────────────────► │ Brave/Chrome │
│ (CLI) │ Chrome DevTools │ (CDP mode) │
└─────────────┘ Protocol └──────────────┘
│ │
│ Zero dependencies │ Isolated profile
│ Pure HTTP + WebSocket │ Separate from your
│ ~2500 lines, single file │ personal browser
└────────────────────────────────────────┘No Puppeteer. No Playwright. No Selenium. Just direct CDP communication.
Comparison
Feature | cdpilot | Puppeteer | Playwright | Selenium |
Install size | ~50KB | 400MB+ | 200MB+ | 100MB+ |
Dependencies | 0 | 50+ | 30+ | Java + drivers |
Setup time | instant | minutes | minutes | painful |
AI-agent ready | yes | manual | manual | manual |
Browser download | no | yes (Chromium) | yes (3 browsers) | no |
CLI-first | yes | no (library) | no (library) | no |
MCP support | yes | no | no | no |
Monetization / Pro (Coming Soon)
cdpilot CLI is and will always be free and open source (MIT).
Future paid offerings:
cdpilot cloud — Remote browser instances, no local browser needed
Team dashboard — Shared sessions, audit logs, usage analytics
Priority support — Direct help for enterprise integrations
Security
Isolated browser profile — cdpilot runs in
~/.cdpilot/profile, separate from your daily browser. Your cookies, passwords, and history are never exposed.No arbitrary file access — MCP screenshot filenames are sanitized and restricted to the screenshots directory. Path traversal is blocked.
Safe CSS selectors — All selectors passed to
querySelectorare JSON-escaped to prevent injection.No network exposure — CDP listens on
127.0.0.1only. Remote connections are not possible by default.No dependencies — Zero npm/Python runtime dependencies means zero supply-chain attack surface.
Found a vulnerability? Please email the maintainer directly instead of opening a public issue.
Roadmap
We're building cdpilot into the lightweight alternative to Playwright MCP for AI agents. Here's what's coming:
40+ CLI commands (navigate, click, fill, screenshot, PDF, console, network...)
MCP server for AI agent integration (Claude Code, etc.)
Visual feedback system (green glow, cursor visualization, click ripples, keystroke display)
AI control warning toast (appears when user tries to interact during automation)
Multi-project browser isolation (each project gets its own port + profile automatically)
DevExtension system (native JS injection without browser store)
Accessibility tree snapshot — structured a11y data for AI agents (like Playwright MCP but 4x lighter)
Annotated screenshots — element references (@e1, @e2) overlaid on screenshots for precise AI clicking
Auto-wait — automatically wait for elements before interaction (reduce flakiness)
Batch commands — pipe JSON arrays via stdin for multi-step automation in one call
iframe & Shadow DOM support — interact with elements inside iframes and shadow roots
Claude Code Skill mode — run as a
.claude/skills/skill in addition to MCPSession recording & replay — record browser sessions and replay them deterministically
Stealth mode — anti-detection flags for web scraping scenarios
Have an idea? Open an issue or submit a PR!
Contributing
git clone https://github.com/mehmetnadir/cdpilot.git
cd cdpilot
npm install
npm testPRs welcome! Please read CONTRIBUTING.md first.
License
MIT — do whatever you want.