leeguooooo f62e204038 fix(stealth,hygiene): per-session stealth coverage + orphaned temp-profile sweep
Stealth coverage (the fork's core value was leaking on secondary surfaces):
- stealth scripts are registered per CDP session, so new tabs (`tab new`) and
  cross-origin iframe sessions created after the initial page had NO patches.
  Extract apply_stealth_via_mgr/apply_stealth_to_session and re-apply on
  tab_new and on iframe attach. Fixes automation markers (and FullLaunch UA)
  leaking in new tabs / cross-origin frames.

Resource hygiene (temp profiles filled the disk):
- ChromeProcess::drop already cleans the temp user-data-dir on normal exit, but
  a hard kill (kill -9 / version-mismatch restart / crash) skips Drop and leaks
  ~50MB per session. Add cleanup_orphaned_chrome_profiles() on daemon startup
  that sweeps agent-browser-chrome-* temp dirs NOT referenced by any live
  process (so an in-use profile is never deleted).
2026-06-01 12:38:57 +09:00
2026-01-10 13:08:22 -06:00
2026-01-10 23:40:54 -06:00

agent-browser-stealth

Stealth fork of agent-browser — connects to your real Chrome, shares your login sessions, and is undetectable by anti-bot systems.

For basic usage, commands, and API reference, see the upstream documentation.

Why this fork?

agent-browser launches a fresh browser with an empty profile. You need to log in again, and websites can detect it's automated.

agent-browser-stealth connects to your existing Chrome. Your cookies, sessions, and browser fingerprint are all real — because it IS your real browser.

agent-browser agent-browser-stealth
Browser Launches new Chrome Connects to your Chrome
Login state Empty, need to re-login Your existing sessions
Fingerprint Automation markers present Your real fingerprint
User collaboration Separate window Same window, take over anytime
CAPTCHA Agent stuck You solve it, agent continues

Install

npm install -g agent-browser-stealth

Install the AI agent skills

The repo ships SKILL.md files for Claude Code, Cursor, etc. Pull them into the current project with skills.sh:

npx skills add leeguooooo/agent-browser-stealth

This drops skills/agent-browser (and the specialized skill-data/{core,electron,slack,dogfood,agentcore,vercel-sandbox}) into your project so your AI agent gets the right usage patterns and pre-approved bash permissions for agent-browser, agent-browser-stealth, and abs.

Setup (one time)

Enable Chrome DevTools Protocol in your Chrome:

  1. Open chrome://inspect/#remote-debugging in Chrome
  2. Toggle the switch on

That's it. This setting persists across Chrome restarts.

Usage

# Connect to your Chrome and navigate
agent-browser open https://example.com

# Everything works through your logged-in browser
agent-browser click "Post"
agent-browser fill "Title" "Hello World"
agent-browser screenshot ./page.png

The agent operates in your Chrome — you'll see tabs opening, pages loading, clicks happening in real time. You can take over at any point (e.g. solve a CAPTCHA), then let the agent continue.

Standalone mode

If you need a separate browser (CI, testing, etc.):

agent-browser --launch open https://example.com

In CI environments, standalone mode is used automatically.

Anti-detection

When connected to your real Chrome, we inject zero JavaScript patches. Your browser's fingerprint is completely genuine.

The only thing we do is call Emulation.setAutomationOverride via CDP to set navigator.webdriver = false at the native Chrome level — undetectable by lie-detection systems like CreepJS.

Test results (connected to real Chrome):

Test site Result
CreepJS 0% stealth, 0% headless
bot.sannysoft.com All green
Cloudflare Turnstile Passed

When using --launch mode (standalone browser), a full suite of 32 stealth patches is applied for headless Chrome.

Differences from upstream

Based on agent-browser v0.27.0. Changes:

  • Auto-connect is defaultagent-browser open <url> connects to your Chrome instead of launching a new one
  • CDP-native stealthEmulation.setAutomationOverride instead of JS patches
  • Dual stealth mode — zero patches for real Chrome, full patches for --launch mode
  • --launch / --new flag — explicitly start a standalone browser
  • CI auto-detection — standalone mode when CI env var is set

All upstream features (commands, snapshots, screenshots, recordings, tabs, sessions, etc.) work the same. See the upstream repo for full documentation.

License

Apache-2.0 (same as upstream)

S
Description
chrome-use — fast browser automation CLI for AI agents (mirror from github.com/leeguooooo/chrome-use)
Readme
29 MiB
Languages
Rust 89.6%
JavaScript 8%
HTML 1.2%
Shell 1.1%
CSS 0.1%