Agent Switchboard
P

Page Agent

by Alibaba

VerifiedOfficial

Official listing: built and published by Alibaba. More from Alibaba

Embeds a GUI agent in any web page with one script tag, driving the existing DOM from natural-language instructions without screenshots or a headless browser.

Access
MCPExtension
Auth
API Key
Skills
5

Skills

  • In-Page Task Execution

    Executes natural-language instructions on the current page by reading a text-based DOM tree, then clicking, typing and scrolling.

  • Smart Form Filling

    Collapses long click-through workflows in ERP, CRM and admin systems into a single sentence that fills and submits page forms.

  • Bring Your Own Model

    Connects to mainstream or locally deployed models through an OpenAI-compatible baseURL and API key set at agent construction.

  • Multi-Page Tasks

    Extends a task across browser tabs using the optional Chrome extension, coordinating steps that span more than one page.

  • MCP Remote Control

    Exposes the in-page agent through a beta MCP server so external agent clients can drive the user own browser session.

Browser & Computer UseCode & DevToolsdom-automationin-page-agentjavascript-librarynatural-language-uiform-fillingchrome-extensiontypescriptweb-accessibility
Visit Agent

Related Agents

Full Self Browsing

Extension · MCP

Automates browser tasks via DOM using your real Chrome profile — persistent auth, 50+ actions, memory system, MCP…

Verifiedby Lakshman Turlapati · Browser & Computer Use · API Key

agent-browser

CLI · MCP

Lets coding agents drive Chrome from a native Rust CLI or stdio MCP server, using accessibility snapshots with element…

VerifiedOfficialby Vercel Labs · Browser & Computer Use · 5 skills · No auth

Browser Use

API · CLI · MCP

Open-source Python library for AI browser automation. Control any website with natural language; cloud adds stealth…

VerifiedFeaturedby Browser Use · Browser & Computer Use · 5 skills · API Key

AgentQL MCP

API · MCP · Extension

Extracts structured web data using natural language queries — no XPath or selectors needed. Works via Python/JS SDKs…

Verifiedby TinyFish · Browser & Computer Use · 3 skills · API Key
page-agent
Embeds a GUI agent in any web page with one script tag, driving the existing DOM from natural-language instructions without screenshots or a headless browser.
fields
namePage Agent
providerAlibaba
urlhttps://alibaba.github.io/page-agent/
categoriesbrowser-computer · code-devtools
accessmcp · browser-extension
authapiKey
streamingfalse
pushfalse
verifiedtrue
officialtrue · Alibaba
tagsdom-automation, in-page-agent, javascript-library, natural-language-ui, form-filling, chrome-extension, typescript, web-accessibility
skills
page-task-executionIn-Page Task ExecutionExecutes natural-language instructions on the current p…
smart-form-fillingSmart Form FillingCollapses long click-through workflows in ERP, CRM and …
bring-your-own-modelBring Your Own ModelConnects to mainstream or locally deployed models throu…
multi-page-tasksMulti-Page TasksExtends a task across browser tabs using the optional C…
mcp-remote-controlMCP Remote ControlExposes the in-page agent through a beta MCP server so …
→ https://alibaba.github.io/page-agent/