docs: lead with the hook, not a feature matrix
The comparison read like a checklist (Runtime.enable leak, permissions footprint — proof, not pitch). Reframe the opening around the visceral wins: - headline: "Give your AI agent the browser you already live in" - pain→relief lead: no fresh Chrome, no re-login, no captcha walls; you watch it work and take the wheel on 2FA; undetectable because it IS your browser (0% bot) - three plain "why not just use X?" lines (Playwright/browser-use, Claude in Chrome, raw debug port) instead of a wall of checkmarks - the honest feature matrix moves into a collapsible "Full feature comparison". Mirrored in README.zh.md.
This commit is contained in:
leeguooooo
@@ -8,9 +8,20 @@ Stealth fork of [agent-browser](https://github.com/vercel-labs/agent-browser)
|
|||||||
|
|
||||||
For basic usage, commands, and API reference, see the [upstream documentation](https://github.com/vercel-labs/agent-browser).
|
For basic usage, commands, and API reference, see the [upstream documentation](https://github.com/vercel-labs/agent-browser).
|
||||||
|
|
||||||
## Why not just use Claude's Chrome extension, web-access, or Playwright?
|
## Give your AI agent the browser you already live in
|
||||||
|
|
||||||
Each alternative solves *part* of the problem. agent-browser-stealth is the only one that does all of it — **drive your own logged-in Chrome, from any tool, with no consent popup, undetectably, and with many agents at once.**
|
**No fresh Chrome. No re-login. No "are you a robot?" walls.**
|
||||||
|
|
||||||
|
agent-browser-stealth points **any** agent — Claude Code, Cursor, Codex, your own scripts — at the **Chrome you're already signed into everything on**. It clicks in *your* window, so you watch it work and grab the wheel the moment it hits a 2FA prompt or captcha. And because it's literally your real browser (over a one-click extension, native messaging — no debug port), sites read it as 100% human: **[CreepJS scores it 0% bot](#anti-detection).**
|
||||||
|
|
||||||
|
**Why not just use…**
|
||||||
|
|
||||||
|
- **Playwright / Puppeteer / browser-use?** They boot an *empty* browser — so you redo every login, fight every captcha, and still get flagged as automation. We use the session you already have.
|
||||||
|
- **Claude's Chrome extension?** Great, but it only drives Claude. This drives *any* agent or CLI.
|
||||||
|
- **A raw `--remote-debugging-port`** (web-access, etc.)? Chrome 136+ pops **"Allow remote debugging?"** on *every* connect. This never does — one-click Store extension, native messaging.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary><b>Full feature comparison</b> (the receipts)</summary>
|
||||||
|
|
||||||
| | [Claude in Chrome](https://www.anthropic.com/claude/chrome) | web-access / raw CDP port | Playwright · Puppeteer · browser-use | **agent-browser-stealth** |
|
| | [Claude in Chrome](https://www.anthropic.com/claude/chrome) | web-access / raw CDP port | Playwright · Puppeteer · browser-use | **agent-browser-stealth** |
|
||||||
|---|:---:|:---:|:---:|:---:|
|
|---|:---:|:---:|:---:|:---:|
|
||||||
@@ -22,9 +33,9 @@ Each alternative solves *part* of the problem. agent-browser-stealth is the only
|
|||||||
| Many agents on **one** real Chrome, isolated tab groups³ | ❌ single app | ⚠️ shared tabs, no isolation | ❌ separate browsers | ✅ |
|
| Many agents on **one** real Chrome, isolated tab groups³ | ❌ single app | ⚠️ shared tabs, no isolation | ❌ separate browsers | ✅ |
|
||||||
| Permissions footprint | 16 incl. `<all_urls>` | full CDP | full control | **7, no `<all_urls>`** |
|
| Permissions footprint | 16 incl. `<all_urls>` | full CDP | full control | **7, no `<all_urls>`** |
|
||||||
|
|
||||||
> Short version: **Claude in Chrome** is great but locked to Claude; **web-access / raw `--remote-debugging-port`** pops Chrome 136+'s consent dialog on every attach; **Playwright/Puppeteer/browser-use** launch a *fresh* browser (no login, automation-flagged, often headless → detected). agent-browser-stealth drives the Chrome you're already signed into, over a native-messaging extension, and reads as a 100% real human browser.
|
<sub>¹ All three real-Chrome tools score ~0% on CreepJS (it's a real browser); we've measured ours. ² rebrowser's `runtimeEnableLeak` — verified clean on our relay path; Claude in Chrome not independently tested (—). ³ web-access can run parallel sub-agents on one browser, but without per-session isolation; each `--session` here gets its own colored, command-isolated tab group. See [Anti-detection](#anti-detection) for the measured numbers.</sub>
|
||||||
>
|
|
||||||
> <sub>¹ All three real-Chrome tools score ~0% on CreepJS (it's a real browser); we've measured ours. ² rebrowser's `runtimeEnableLeak` — verified clean on our relay path; Claude in Chrome not independently tested (—). ³ web-access can run parallel sub-agents on one browser, but without per-session isolation; each `--session` here gets its own colored, command-isolated tab group. See [Anti-detection](#anti-detection) for the measured numbers.</sub>
|
</details>
|
||||||
|
|
||||||
## Why this fork?
|
## Why this fork?
|
||||||
|
|
||||||
|
|||||||
+16
-5
@@ -8,9 +8,20 @@
|
|||||||
|
|
||||||
基础用法、命令与 API 参考见[上游文档](https://github.com/vercel-labs/agent-browser)。
|
基础用法、命令与 API 参考见[上游文档](https://github.com/vercel-labs/agent-browser)。
|
||||||
|
|
||||||
## 为什么不用 Claude 的 Chrome 插件、web-access 或 Playwright？
|
## 把你**已经登录好**的浏览器，交给你的 AI agent
|
||||||
|
|
||||||
每个同类方案只解决了问题的**一部分**。agent-browser-stealth 是唯一全做到的 —— **驱动你自己已登录的 Chrome、任意工具都能调、不弹同意框、不可检测、还能多 agent 并发。**
|
**不用开新 Chrome。不用重新登录。不用跟"你是不是机器人"较劲。**
|
||||||
|
|
||||||
|
agent-browser-stealth 让**任意** agent（Claude Code、Cursor、Codex、你自己的脚本）直接操作你**已经登录了所有网站**的那个 Chrome。它在**你的窗口里**点击，你看着它干活，撞到 2FA / 验证码的瞬间你接管一下，它接着跑。因为它**就是你的真实浏览器**（一键装的扩展、原生消息、无调试端口），网站眼里它 100% 是人：**[CreepJS 实测 0% 机器人](#反检测)。**
|
||||||
|
|
||||||
|
**为什么不用……**
|
||||||
|
|
||||||
|
- **Playwright / Puppeteer / browser-use？** 它们开的是**空**浏览器 —— 每个登录你重做、每个验证码你硬扛、最后还被标成自动化。我们直接用你**现成的**会话。
|
||||||
|
- **Claude 的 Chrome 插件？** 很好，但**只能给 Claude 用**。我们给**任意** agent / CLI 用。
|
||||||
|
- **裸 `--remote-debugging-port`**（web-access 等）？ Chrome 136+ **每次连都弹** "Allow remote debugging?"。我们**永不弹** —— 商店一键装，原生消息。
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary><b>完整对比矩阵</b>（要细节的看这里）</summary>
|
||||||
|
|
||||||
| | [Claude in Chrome](https://www.anthropic.com/claude/chrome) | web-access / 裸 CDP 端口 | Playwright · Puppeteer · browser-use | **agent-browser-stealth** |
|
| | [Claude in Chrome](https://www.anthropic.com/claude/chrome) | web-access / 裸 CDP 端口 | Playwright · Puppeteer · browser-use | **agent-browser-stealth** |
|
||||||
|---|:---:|:---:|:---:|:---:|
|
|---|:---:|:---:|:---:|:---:|
|
||||||
@@ -22,9 +33,9 @@
|
|||||||
| 多 agent 共用**同一个**真实 Chrome、标签组隔离³ | ❌ 单 app | ⚠️ 共享 tab、无隔离 | ❌ 各开各的浏览器 | ✅ |
|
| 多 agent 共用**同一个**真实 Chrome、标签组隔离³ | ❌ 单 app | ⚠️ 共享 tab、无隔离 | ❌ 各开各的浏览器 | ✅ |
|
||||||
| 权限面 | 16 个，含 `<all_urls>` | 完整 CDP | 完全控制 | **7 个，无 `<all_urls>`** |
|
| 权限面 | 16 个，含 `<all_urls>` | 完整 CDP | 完全控制 | **7 个，无 `<all_urls>`** |
|
||||||
|
|
||||||
> 一句话：**Claude in Chrome** 很好，但只能给 Claude 用；**web-access / 裸 `--remote-debugging-port`** 每次连接都会弹 Chrome 136+ 的同意框；**Playwright/Puppeteer/browser-use** 启的是**全新**浏览器（没登录、带自动化标记、常 headless → 被识破）。agent-browser-stealth 直接开你**已经登录好**的那个 Chrome，走原生消息扩展，在检测站上读起来就是个 100% 真人浏览器。
|
<sub>¹ 三家"真实 Chrome"工具在 CreepJS 上都 ~0%（毕竟是真浏览器），我们的是实测过的。² rebrowser `runtimeEnableLeak` —— 我们的中继路径实测无泄漏；Claude in Chrome 未独立测试（—）。³ web-access 也能跑并行子 agent，但无每会话隔离；本工具每个 `--session` 拿到自己彩色、命令隔离的标签组。实测数字见 [反检测](#反检测)。</sub>
|
||||||
>
|
|
||||||
> <sub>¹ 三家"真实 Chrome"工具在 CreepJS 上都 ~0%（毕竟是真浏览器），我们的是实测过的。² rebrowser `runtimeEnableLeak` —— 我们的中继路径实测无泄漏；Claude in Chrome 未独立测试（—）。³ web-access 也能跑并行子 agent，但无每会话隔离；本工具每个 `--session` 拿到自己彩色、命令隔离的标签组。实测数字见 [反检测](#反检测)。</sub>
|
</details>
|
||||||
|
|
||||||
## 为什么要 fork
|
## 为什么要 fork
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user