I filled in [email protected] and test-password-123, clicked Sign up, and the page showed a welcome message. One image and the favicon failed to load.
What the page shows after submitting
- The heading is still "Join Recipe Club", and the form is still there with both fields filled in.
- A new paragraph reads exactly: "Welcome, [email protected]!". The email is shown in all caps, although I typed it in lowercase.
- Below that is an image with the alt text "logo". It is the one that failed to load (see below).
Resources that failed to load
GET http://127.0.0.1:8765/missing.png(Image) returned 404. This looks like the "logo" image, so it probably shows as broken.GET http://127.0.0.1:8765/favicon.icoreturned 404.- The page document itself (
index.html) loaded with a 200.
I did not check the browser console for JavaScript errors beyond the network requests above.
How it was tried: I installed agent-browser 0.27.0 into a temporary folder (not globally) and ran it with a throwaway home directory, restricted to one local test page I built (a sign-up form with a deliberately missing image and an email-uppercasing handler). Only Skill and agent-browser commands were allowed, with no logins or other sites. The browser download step was not run. I repeated the same steps by hand and got the same page text and the same two 404s. Not tried: logging in, the credential vault, Slack, Electron apps, recording, and any real website.
它做什麼
agent-browser 的一個簡短探索檔案。agent-browser 是為 AI 代理設計的瀏覽器自動化命令列工具,透過 DevTools 協定驅動 Chrome 或 Chromium,用無障礙樹快照與精簡的元素參照來操作,不依賴 Playwright 或 Puppeteer。
運作方式
- 先安裝一次程式:
npm i -g agent-browser && agent-browser install。 - 這個檔案只是個入口。執行任何指令之前,代理會用
agent-browser skills get core從命令列載入真正的使用說明,所以說明始終與已安裝的版本一致。 - 另有專門的指南,涵蓋 Electron 桌面應用、Slack、探索性測試與 QA、從錄製的流量推導 API 用戶端、Vercel Sandbox、受保護的 Vercel 部署,以及 AWS Bedrock AgentCore 雲端瀏覽器。
- 可選的可觀測性面板執行在 4848 連接埠。
適合情境
網站自動化、填表、截圖、資料擷取、網頁應用測試。它控制的是真實瀏覽器,並且能登入網站,請先看風險說明。
高風險:這個包只是一個很短的指引檔案。它讓代理去全域安裝一個 npm 程式(`npm i -g agent-browser && agent-browser install`),並從該程式載入真正的使用說明,所以實際的指引不在本包裡,並且隨你安裝的版本而變。這個程式能驅動真實的 Chrome:開啟網站、點擊、填寫並送出表單、登入(自帶憑證保險庫)、在頁面上執行 JavaScript、上傳檔案、錄製流量與影片,還能自動化桌面應用與 Slack。瀏覽器登入了什麼,它就能對什麼動手。請使用獨立的工作階段或設定檔,盡量限定可存取的網域,不要在你承受不起誤操作的帳號上執行,並留意它在做什麼。需要 Node.js 與網路。該 Skill 的描述還要求代理優先使用它,而不是內建的瀏覽器工具。 已試用一次:在隔離環境裡(暫存家目錄、只允許存取 localhost、不登入任何帳號)對我自己架的本機測試頁操作,正確完成了填表、送出、讀取結果,並列出了載入失敗的請求。登入、憑證保險庫、Slack、桌面應用、錄製與真實網站都沒有試,並且模型試用後沒有關閉瀏覽器工作階段。