Observe
Read pages, tabs, element outlines and current window state.
A visible WebView2 browser workspace for AI Agents.
See what AgentBrowser can do, which steps need human confirmation and how it connects to your existing AI workflow.
Architecture
Browser, protocol and authorization are separate layers.
Every step—from observing the page and checking permission to real actions and human handoff—has a clear boundary.
Authorize
Authorize advanced actions, downloads and window control first.
Act
Log clicks, input, scrolling, tab switches and downloads in the protocol.
Handoff
Let users visibly complete sign-in, CAPTCHAs and payment.
Agent integration example
Any Agent framework that can send HTTP requests can connect.
POST /agent/v2/act
{ "action": "click", "selector": "#submit-btn" }
→ 200 OK
{ "ok": true, "result": "clicked" }
LangChain, AutoGen and custom Agent frameworks can connect over HTTP; Human Handoff covers sign-in, CAPTCHAs and payments.
Window control
Maximize, minimize, bring forward, capture screenshots and switch tabs.
Download distribution
Publish installers and updates centrally to avoid version confusion.
Audit records
Record key actions in protocol logs for diagnosis and testing.
Device binding
Query accounts, device fingerprints and plan rights together.