- 每月造訪次數
- 34.3K
- 上升36.6%較上月2026 年 9 月
- 公開營收
- 未公開
- 暫無公開營收證據
- 入門價
- $9.99/月
- 低於同類 87% 的產品同類中位數 $25.46/月
- 首次發布
- 23 個月前
- 2024-12-23 · 估算
訪問
行銷動作
發布、搜尋與內容、引薦、促銷在 Product Hunt 發布發布
Free AI browser agent: find leads, reach out, apply to jobs
10 月 14 日 · 31 天前發布頁
當時 每月造訪次數 34.3K同期還有 12 個動作在 Show HN 發布(9 分)發布
DeepSeek Flash inverted the economics of agent products — There is an adversarial relationship between developers and big model labs. Model labs charged developers higher API prices to subsidize t…
6 月 25 日 · 5 個月前發布頁
在 Show HN 發布(2 分)發布
AI agents should browse your site, not call your API — We compared four architectures for putting AI agents on websites — RAG bots, API-tool agents(WebMCP), code-writing sandboxes (Cloudflare A…
4 月 17 日 · 7 個月前發布頁
在 Show HN 發布(46 分 · 17 評論)發布
AI Subroutines – Run automation scripts inside your browser tab — We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM infer…
4 月 17 日 · 7 個月前發布頁
在 Show HN 發布(5 分)發布
MCP is for tools. A2A is for agents. What's for websites? — HTTP lets agents fetch pages. Cloudflare's Markdown for Agents lets them fetch more efficiently. MCP (Anthropic) connects agents to develo…
4 月 12 日 · 7 個月前發布頁
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- 創作者原帖摘錄:
- Hey HN, I'm excited to share rtrvr.ai, a Chrome extension that brings the power of AI agents to your everyday web browsing. It's designed to automate complex web tasks, extract structured data from any website, and integrate with your favorite tools as you browse using AI Function Calling [ie: “Send this page summary as Slack message”]. The core idea is to l
- 創作者原帖摘錄:
- We initially launched rtrvr.ai: an AI Web Agent Chrome Extension that can autonomously complete tasks, scrape data to Sheets and call API's as you browse Chrome with just prompts! We showcased out AI Agent: - Researching and Trading Stocks: https://www.youtube.com/watch?v=1glo1GuojeM - Automating LinkedIn Outbound: https://www.youtube.com/watch?v=Ct__f-fLS8A
- 創作者原帖摘錄:
- We just benchmarked our agent, rtrvr.ai, on the Halluminate (YC S25) Web Bench, and rtrvr.ai achieved a new State-of-the-Art performance with an 81% success rate. For perspective, this surpasses not only all other autonomous agents but also the human-intervention baseline of OpenAI's Operator (76.5%). It also completes tasks an astonishing 7x faster than the
- 創作者原帖摘錄:
- Hey HN, I'm Arjun, one of the founders of rtrvr.ai. For the past year, we've been building and iterating on an in-browser AI agent. But a few months ago, we hit a wall in our approach and decided to tear everything down and rebuild from first principles. The result is what we're re-launching today. The Problem/Insight: We kept coming back to a simple, naggin
- 創作者原帖摘錄:
- Hi HN, Bhavani here (rtrvr.ai). We build DOM-native web agents (no screenshot-based vision, no CDP/Playwright debugger-port control). We handle captchas natively including Google reCAPTCHA image challenges by traversing cross-origin iframes and shadow DOM. The latency is high on this one currently. The problem: when debugging image selection captchas ("selec
- 創作者原帖摘錄:
- Rover is the world's first Embeddable Web Agent, a chat widget that lives on your website and takes real actions for your users. Clicks buttons. Fills forms. Runs checkout. Guides onboarding. All inside your UI. One script tag. No APIs to expose. No code to maintain. We built Rover because we think websites need their own conversational agentic interfaces as
- 創作者原帖摘錄:
- HTTP lets agents fetch pages. Cloudflare's Markdown for Agents lets them fetch more efficiently. MCP (Anthropic) connects agents to developer-defined tools. A2A (Google) lets agents delegate to other agents. But there's a missing layer: how does an agent execute a multi-step task on a website -- add to cart, fill a form, complete a checkout - with the site o
- 創作者原帖摘錄:
- We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM inference delay, and zero mistakes. The subroutine itself is a deterministic script composed of discovered network calls hitting the site's backend as well as page interactions like click/type/find. The key architectural decisi
- 創作者原帖摘錄:
- We compared four architectures for putting AI agents on websites — RAG bots, API-tool agents(WebMCP), code-writing sandboxes (Cloudflare Agent Lee), and DOM-native execution. Three of them force you to maintain a parallel engineering surface. The DOM already has live state, user auth, and permissions baked in. A structural breakdown of why.
- 創作者原帖摘錄:
- There is an adversarial relationship between developers and big model labs. Model labs charged developers higher API prices to subsidize their own agent harness offerings. Think Anthropic charging 5x higher Claude API prices to subsidize consumer subscriptions. So Cursor in a way was subsidizing their own direct competitor. DeepSeek V4 Flash totally inverted
開源倉庫與 Agent 生態
商店資料
- 評分
- 評分未同步評分數未同步
- 上月新增評分
- —
- 價格與內購
- 免費內購資料未同步
- 當前版本
- —商店公開檔案
商店圖示、評分分布、安裝量級與宣傳截圖同步自 Apple App Store、Google Play 與 Chrome 應用商店。
流量來源
訪問構成
管道
- 直接訪問54%
- 自然搜尋29%
- 社交媒體11%
- 其他6%
國家/地區
- 美國42%
- 印度19%
- 加拿大8%
- 南韓4%
- 法國4%
搜尋
站點權重 —網域名稱註冊 2023-11-09
| 關鍵字 | 月搜尋量 |
|---|---|
| retriever ai | 1,470 |
| rtrvr ai | 930 |
| retreaver affiliate group community | 240 |
| retriver ai | 240 |
| rtrvr | 90 |
流量資料:Vaneform
定價
試用:未提供 · 4 檔付費($9.99–$499.99) · 年付最高省 17% · 觀察於 2026-11-04 · 原定價頁
入門價 $9.99/月,低於同類 87% 的產品;「智慧體構建平台」中位數 $25.46/月。查看定價基準
頁面與變化
關鍵頁面
每週快照變化
設計
暖白底配黑色大標題,右側手繪公園插畫,底部疊放彩色描邊任務卡片,整體柔和親切。
首屏畫面預覽 · 點擊放大
首屏畫面講了什麼與轉化路徑
“Your free AI browser agent.”
左對齊標題與按鈕,右側插畫鋪滿,底部居中疊放任務卡片。
首屏畫面轉化路徑:左文右圖 + 插畫、手繪或卡通角色 → 下載用戶端 / 安裝外掛 · 配合使用者數、星級或核心指標建立信任
色板 · 點擊複製
- 字體與排版
- 8.0
- 色彩與對比
- 8.0
- 構圖與留白
- 8.0
- 細節與工藝
- 8.0
- 風格辨識度
- 7.0
結構
- 字體
- Inter
- 首屏畫面版式
- 左文右圖
- 主視覺
- 插畫、手繪或卡通角色
- 轉化動作
- 下載用戶端 / 安裝外掛
- 信任背書
- 使用者數、星級或核心指標
- 導航
- 頂部通欄導航
- 明暗與密度
- 淺色 · 適中
- 圓角與層級
- 小圓角 · 細線分層
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:柔和友好(兼備雜誌排版)
低飽和粉彩、大圓角與圓潤字體,配友好的插畫,面向大眾使用者。
## 設計參數
```css
:root {
--background: #f6f3ea;
--surface: #ffffff;
--foreground: #111111;
--muted-foreground: #6b6b6b;
--accent: #e4572e;
--radius: 4px;
--font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
}
```
色彩面積配比:背景 #F6F3EA(約 46%) · 面板 #FFFFFF(約 12%) · 正文 #111111(約 16%) · 次要文字 #6B6B6B(約 8%) · 強調 #E4572E(約 18%)。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:左文右圖
- 導航結構:頂部通欄導航
- 明暗與密度:淺色 · 適中
- 圓角與層級:小圓角;不用陰影,用細線與留白區分層級
- 主視覺載體:插畫、手繪或卡通角色
- 轉化動作:下載用戶端 / 安裝外掛 · 信任背書採用使用者數、星級或核心指標
- 標題切入點:品類定位錨點
- 首屏畫面元件特徵:插畫、資料指標欄、懸浮多卡片
- 空間布局拆解:左對齊標題與按鈕,右側插畫鋪滿,底部居中疊放任務卡片。
- 視覺特徵總結:暖白底配黑色大標題,右側手繪公園插畫,底部疊放彩色描邊任務卡片,整體柔和親切。
## 避免
- 純黑大面積
- 直角
- 等寬字體
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
- Rtrvr.ai 的價格是多少?
- Free: $0; Starter: $9.99/月(提供年付); Pro: $29.99/月(提供年付); Team: $99.99/月(提供年付); Scale: $499.99/月(提供年付). 觀察於 2026-11-04。 當前計費條件、用量限制與稅費以來源頁面為准。來源
- Rtrvr.ai 的網站造訪次數是多少?
- Vaneform 估算 2026-09 網站造訪次數為 34.3K。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
- Rtrvr.ai 是什麼產品,支援哪些平台?
- Rtrvr.ai 歸屬「智慧體構建平台」市場領域:Retriever AI 是面向建造者、GTM團隊和創辦人的 AI 瀏覽器代理,可跨網站自動完成研究、外聯及日常工作並返回結果。。 支援平台包括:瀏覽器擴充功能、MCP 服務、CLI 與 SDK、開放 API。
- Rtrvr.ai 是開源專案嗎?採用什麼協議?
- Rtrvr.ai 擁有公開程式碼倉庫(https://github.com/rtrvr-ai/rover),已公開原始碼倉庫,記錄有 22 個 GitHub Stars。來源
同分類研究對象
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。