為AI代理提供可保持身份、登入狀態並執行瀏覽器任務的獨立瀏覽器，適用於需要自動化瀏覽器操作的個人和團隊。
scalebrowser.net AI 模型與智慧體 / 智慧體工具與 MCP
- 每月造訪次數
- 162K
- 上升212.7%較上月2026 年 10 月
- 公開營收
- 未公開
- 暫無公開營收證據
- 入門價
- $19/月
- 高於同類 48% 的產品同類中位數 $19/月
- 首次發布
- 41 天前
- 2026-10-06 · 估算
訪問
近 12 個月
行銷動作
發布、搜尋與內容、引薦、促銷Scalebrowser launched on Fazier（#78 · 17 票 · 1 評論）發布
Scalebrowser — Human browser capabilities. Now for AI agents.
11 月 11 日 · 5 天前原文證據
當時 每月造訪次數 162K同期還有 2 個動作Scalebrowser launched on Fazier（#87 · 12 票 · 1 評論）發布
Scalebrowser — Human browser capabilities. Now for AI agents.
11 月 11 日 · 5 天前原文證據
當時 每月造訪次數 162K同期還有 2 個動作Scalebrowser launched on Product Hunt發布
Human browser capabilities. Now for AI agents.
10 月 16 日 · 31 天前原文證據
當時 每月造訪次數 51.8K訪問：之前 1 個月 +175%，之後 1 個月 +213%同期還有 3 個動作Scalebrowser launched on Findly.tools發布
Scalebrowser runs persistent browser profiles on your own machines so AI agents stay signed in, pass verification, and finish real work.
10 月 6 日 · 41 天前原文證據
當時 每月造訪次數 51.8K訪問：之前 1 個月 +175%，之後 1 個月 +213%同期還有 1 個動作
第三方評測與案例拆解
客戶來源管道拆解、工程師評測與開源檔案Findly.tools
2026-10-06查看原文
- 核心亮點評測：
- Scalebrowser is self-hosted browser infrastructure for teams running AI agents. Each agent gets an isolated profile with a persistent identity that survives restarts and encrypted moves between your machines. Cookies, logins, passkeys, memory, and tasks remain with it. A patched Chromium fork works below the page instead of covering automation traces with scripts. It uses the real GPU and screen in your machine, rejects contradictory identities, and sends every click, keystroke, and scroll through a human-like input layer. Agents can handle email and SMS codes, generate TOTP, solve 18 measured captcha types, and respond to browser permission prompts. Scalebrowser connects over MCP, REST, Node.js, Python, or direct CDP. Compact page maps and deltas reduce model context, while run trails, per-step screenshots, secret filtering, and server-side limits make work observable and controllable. Profiles are unlimited on every plan; pricing is based only on concurrent browsers and machines.
Fazier
2026-11-11查看原文
- 核心亮點評測：
- - **One real browser per agent.** Each profile has its own cookies, saved logins, passkeys, extensions and files. The agent working on a client's Facebook page can't see your LinkedIn. - **Sessions that last.** Cookies and passkeys survive a crash, an update and a closed window, so the next run starts signed in. - **Sign-in without handing over the password.** You save it once, encrypted, on your PC. The agent names the field and the password is typed for it, so it never shows up in a prompt or a log. - **A mailbox for every profile.** Bind an email address to a profile and the agent reads confirmation codes and sign-in links there. A saved authenticator key gives it the six digits that change every 30 seconds. - **Human input, always.** Every click follows a real pointer path and every key has its own timing. The agent has no way to skip this layer. - **The page as a list of things to click.** The agent gets the buttons, fields and links with their names, and after each step only what changed. Long runs stay cheap. - **It answers what the browser asks.** Permission prompts, file pickers, download bars and device dialogs get a reply instead of freezing the run. - **Captcha solving.** Any captcha get passed with the normal click and key tools, and there's no paid solver service behind it. - **Record once, replay.** A recording remembers each button by its role and name, so it still finds it after the page has been rebuilt. - **Every step on record.** Each step comes back with its result and a still image. Passwords and other secrets are blacked out in the picture. - **Your PC's own hardware.** GPU, screen, CPU and fonts are the machine's real ones, so nothing on the page contradicts itself. Each profile can have its own proxy, and its time zone and language follow the proxy's country. - **Plugs into what you already use.** MCP for Claude Code, Cursor and other clients, REST, Python and Node SDKs (MIT) or plain CDP.
- 適用人群：
- - **Agents that sign in.** Let an agent work in your LinkedIn, Instagram or a job portal. It signs in with the saved password, reads the confirmation code from the profile's inbox and is still signed in tomorrow. - **Tools with no API.** Midjourney has no public API and Zillow's MLS listing feed is invite only. The agent uses the website the way you do and brings back text, a file or a picture. - **One profile per account.** An agency gives every client's Facebook page its own profile, and each agent opens only its own. Cookies, logins and files stay apart from the first click. - **Work you repeat.** Download the invoice from each vendor portal, open three competitor pages, copy yesterday's orders into a sheet. Do the round once with the agent, then let it repeat it, or put it on a scheduler you already use and it runs every morning. - **A real browser for your agent.** Claude Code or Cursor opens your staging site in a signed-in Chrome, reads the page and clicks through it over MCP.
Fazier
2026-11-11查看原文
- 核心亮點評測：
- - **Persistent identity.** A profile's fingerprint comes from one seed, so it returns as the same machine after a restart, an update or an encrypted move to another computer you own. - **Real hardware, no noise.** Scalebrowser uses the real GPU and screen values and refuses to launch a profile whose identity contradicts itself. No random canvas or WebGL noise. - **Patched Chromium.** Automation traces are removed inside the engine, not hidden by page scripts. - **Human-like input.** Every click, keystroke and scroll is routed through a human-like input layer instead of being injected instantly. - **Sign-in handled.** Encrypted credentials the agent can fill without seeing the password, passkeys that survive browser shutdowns, email and SMS codes, and local TOTP. - **18 captcha types.** Measured as solved on live widgets, including Cloudflare Turnstile, reCAPTCHA, hCaptcha and several GeeTest variants. Arkose and rotation captchas are the documented exceptions. - **Browser prompts exposed.** Permission bubbles, warnings and device pickers show up for the agent instead of silently blocking the run. - **Less context.** 21 tools by default out of 62, and a compact page map followed only by what changed. In Scalebrowser's own benchmark that took 11x fewer tokens than Playwright MCP over 75 steps. - **Run trail and limits.** Every tool call becomes a step with its result and a screenshot. Read-only mode and address rules are enforced server-side, and secrets found on a page are replaced before they reach the model. - **Fleet controls.** Group, reserve, start and stop profiles in bulk, assign your own proxies and extensions, and sync selected profiles between your machines with encryption. - **Recipes and video.** Save a working run as a reusable recipe, or turn it into a demo video with camera movement, cursor motion, voiceover and subtitles.
- 適用人群：
- - **Work inside real accounts.** Log in with two-factor, stay signed in and finish jobs in tools that have no API. - **Daily jobs under one identity.** Run the same task every morning and show up as the same visitor each time. - **Many agent identities on your own hardware.** Keep dozens of persistent profiles, grouped and reserved per agent, with credentials, passkeys and recordings staying on your machines. - **Replace a cloud browser API or a Playwright stealth stack.** Attach your existing Playwright or Puppeteer code over CDP, or point an MCP client at it, and keep the sessions local. - **Check what an agent did.** Read the run trail step by step, with a screenshot for each one, and switch on read-only mode for sensitive accounts. - **Product demos and proof records.** Turn a completed run into a demo video, or render it as an unbroken proof record.
MCP 服務與 Agent 生態
GitHub 開源與智慧體接入
流量來源
2026 年 10 月
訪問構成
管道
- 直接訪問40%
- 自然搜尋25%
- 外部引薦15%
- 展示廣告7%
- 其他14%
國家/地區
暫無資料
搜尋
站點權重 —網域名稱註冊 2026-07-11
| 關鍵字 | 月搜尋量 |
|---|---|
| patchright | 6,370 |
| cdp runtime evaluate | 460 |
| stealth browser github | 200 |
| github nodriver zendriver botasaurus patchright stealth chromium captcha bypass real chrome binary | 190 |
流量資料：Vaneform
定價
Free
$0
1 machine · 1 profile · 3 workflows
Start
$19/月
按年付 $15.83/月省 17%
1 machine · 1 profile · 25 workflows
Solo
$49/月
按年付 $40.83/月省 17%
1 machine · 1 profile · 100 workflows
Studio
$99/月
按年付 $82.5/月省 17%
3 profiles · 500 workflows
Enterprise
聯繫銷售
Unlimited profiles
試用：Start 7-day free trial · 3 檔付費（$19–$99） · 年付最高省 17% · 設企業客製化檔 · 觀察於 2026-11-06 · 原定價頁
入門價 $19/月，高於同類 48% 的產品；「智慧體工具與 MCP」中位數 $19/月。查看定價基準
頁面與變化
開始記錄於 2026-10-16
關鍵頁面
每週快照scalebrowser.net/ 快照 2026-11-06
變化
開始記錄以來，定價、方案與定位都沒有變化。
設計
首屏畫面視覺分析與 :root CSS
白底配深海軍藍文字與按鈕，居中大號幾何無襯線標題，留白充足，底部露出產品介面截圖。
首屏畫面預覽 · 點擊放大
首屏畫面講了什麼與轉化路徑
“Run your browser tasks on autopilot with AI agents”
頂欄下居中標題、副文案與雙按鈕，產品截圖貼在首屏畫面底部。
首屏畫面轉化路徑：標題下方大幅產品介面 + 產品介面截圖或元件示意 → 免費開始 / 立即註冊
- 結果與速度承諾
- 首屏畫面大幅產品介面
色板 · 點擊複製
五維設計評分7.3 / 10
- 字體與排版
- 8.0
- 色彩與對比
- 7.0
- 構圖與留白
- 8.0
- 細節與工藝
- 7.0
- 風格辨識度
- 6.0
結構
- 字體
- TT Neoris
- 首屏畫面版式
- 標題下方大幅產品介面
- 主視覺
- 產品介面截圖或元件示意
- 轉化動作
- 免費開始 / 立即註冊
- 信任背書
- 無顯式背書
- 導航
- 頂部通欄導航
- 明暗與密度
- 淺色 · 留白多
- 圓角與層級
- 中圓角 · 有陰影
預覽 AI 設計說明全文（含 :root CSS 變量與版式規則）只寫風格參數，禁止復刻該產品的品牌名、標誌、文案與圖片
# 設計說明：極簡單色
黑白灰加一個強調色，細線分隔，大量留白，靠字號與字重分層級。
## 設計參數
```css
:root {
--background: #ffffff;
--surface: #f7f8fa;
--foreground: #1d2735;
--muted-foreground: #4b5563;
--accent: #1d2735;
--radius: 8px;
--font-heading: "TT Neoris", ui-sans-serif, system-ui, sans-serif;
--font-body: "TT Neoris", ui-sans-serif, system-ui, sans-serif;
}
```
色彩面積配比：背景 #FFFFFF（約 81%） · 面板 #F7F8FA（約 7%） · 正文 #1D2735（約 6%） · 次要文字 #4B5563（約 4%） · 強調 #1D2735（約 2%）。背景與面板占絕大部分面積，強調色只用於主按鈕與當前激活狀態。
## 版式與轉化結構
- 首屏畫面版式：標題下方大幅產品介面
- 導航結構：頂部通欄導航
- 明暗與密度：淺色 · 留白多
- 圓角與層級：中圓角；用陰影區分層級
- 主視覺載體：產品介面截圖或元件示意
- 轉化動作：免費開始 / 立即註冊
- 標題切入點：結果與速度承諾
- 首屏畫面元件特徵：首屏畫面大幅產品介面
- 空間布局拆解：頂欄下居中標題、副文案與雙按鈕，產品截圖貼在首屏畫面底部。
- 視覺特徵總結：白底配深海軍藍文字與按鈕，居中大號幾何無襯線標題，留白充足，底部露出產品介面截圖。
## 避免
- 多種強調色並用
- 漸層背景
- 重陰影
請按上面的設計參數與版式實現介面：顏色只用這些變量，強調色只給主要操作與當前狀態。只採用這種風格，禁止復刻任何參考產品的品牌名、標誌、文案與圖片。
問題與證據
- Scalebrowser 的價格是多少？
- Free: $0; Start: $19/月（提供年付）; Solo: $49/月（提供年付）; Studio: $99/月（提供年付）; Enterprise: 聯繫銷售. 觀察於 2026-11-06。 當前計費條件、用量限制與稅費以來源頁面為准。來源
- Scalebrowser 的網站造訪次數是多少？
- Vaneform 估算 2026-10 網站造訪次數為 162K。造訪次數包含重複訪問，付費客戶數與收入需分別查看對應證據。來源
- Scalebrowser 是什麼產品，支援哪些平台？
- Scalebrowser 歸屬「智慧體工具與 MCP」市場領域：為AI代理提供可保持身份、登入狀態並執行瀏覽器任務的獨立瀏覽器，適用於需要自動化瀏覽器操作的個人和團隊。。 支援平台包括：MCP 服務、CLI 與 SDK、開放 API。
同分類研究對象
AI 模型與智慧體 / 智慧體工具與 MCP
這些產品屬於同一目錄分類。選型時請進一步核對客戶任務、功能與部署要求。