leeguooooo 3d032f9e88 fix(connect): stop remote-debugging consent storm on transient liveness timeout
The daemon re-validates the CDP connection before every browsing command via
is_connection_alive() (Browser.getVersion, 3s timeout). It treated any
timeout-or-error as "dead" and tore the connection down + reconnected.

For an externally-attached browser (the stealth fork's default — the user's
real Chrome), a timed-out probe is almost always Chrome being briefly busy or
showing the Chrome 136+ "Allow remote debugging?" consent modal, which blocks
CDP responses until the user clicks Allow. Tearing the already-consented
connection down forces a reconnect that re-pops the consent prompt — repeated
on every command this becomes an endless prompt loop, and the close +
multiple new /devtools/browser WS probes storm Chrome into a freeze.

Fix: distinguish the probe outcome.
- Responded      -> alive
- TransportError -> dead (WS closed/reset; user closing Chrome lands here too,
                    so zombie-socket detection is preserved)
- TimedOut       -> alive for an external attach (don't tear down a consented
                    connection on transient slowness); dead for a browser we
                    launched ourselves (a real hang worth reconnecting, and no
                    consent modal in play).

Extracted the verdict into a pure connection_alive_from_probe() with unit
tests covering all outcomes. No behavior change for locally-launched browsers.
2026-06-01 11:36:00 +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 default — agent-browser open <url> connects to your Chrome instead of launching a new one
  • CDP-native stealth — Emulation.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%