Agentic Browser

Browser automation for AI agents via inference.sh.

通过inference.sh为AI Agent实现浏览器自动化。

Quick Start

快速开始

bash

curl -fsSL https://cli.inference.sh | sh && infsh login

bash

curl -fsSL https://cli.inference.sh | sh && infsh login

Open a page and get interactive elements

infsh app run agentic-browser --function open --input '{"url": "https://example.com"}' --session new

undefined

infsh app run agentic-browser --function open --input '{"url": "https://example.com"}' --session new

undefined

Core Workflow

核心工作流

Every browser automation follows this pattern:

Open: Navigate to URL, get element refs
Snapshot: Re-fetch elements after DOM changes
Interact: Use
```
@e
```
refs to click, fill, etc.
Re-snapshot: After navigation, get fresh refs

bash

undefined

所有浏览器自动化都遵循以下模式：

打开：导航至URL，获取元素引用
快照：DOM变化后重新获取元素
交互：使用
```
@e
```
引用进行点击、填写等操作
重新快照：导航完成后获取新的引用

bash

undefined

Start session

RESULT=$(infsh app run agentic-browser --function open --session new --input '{ "url": "https://example.com/login" }') SESSION_ID=$(echo $RESULT | jq -r '.session_id')

Elements returned like: @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Sign In"

Fill form

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "fill", "ref": "@e1", "text": "user@example.com" }'

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "fill", "ref": "@e2", "text": "password123" }'

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "fill", "ref": "@e1", "text": "user@example.com" }'

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "fill", "ref": "@e2", "text": "password123" }'

Click submit

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "click", "ref": "@e3" }'

Close when done

infsh app run agentic-browser --function close --session $SESSION_ID --input '{}'

undefined

infsh app run agentic-browser --function close --session $SESSION_ID --input '{}'

undefined

Functions

功能函数

open

Navigate to URL and configure browser. Returns page snapshot with

@e

refs.

bash

infsh app run agentic-browser --function open --session new --input '{
  "url": "https://example.com",
  "width": 1280,
  "height": 720,
  "user_agent": "Mozilla/5.0..."
}'

Returns:

```
url
```
: Current page URL
```
title
```
: Page title
```
elements
```
: List of interactive elements with
```
@e
```
refs
```
screenshot
```
: Page screenshot (for vision agents)

导航至URL并配置浏览器。返回包含

@e

引用的页面快照。

bash

infsh app run agentic-browser --function open --session new --input '{
  "url": "https://example.com",
  "width": 1280,
  "height": 720,
  "user_agent": "Mozilla/5.0..."
}'

返回内容：

```
url
```
: 当前页面URL
```
title
```
: 页面标题
```
elements
```
: 包含
```
@e
```
引用的可交互元素列表
```
screenshot
```
: 页面截图（供视觉Agent使用）

snapshot

Re-fetch page state after DOM changes. Always call after clicks that navigate.

bash

infsh app run agentic-browser --function snapshot --session $SESSION_ID --input '{}'

DOM变化后重新获取页面状态。点击触发导航的元素后务必调用此函数。

bash

infsh app run agentic-browser --function snapshot --session $SESSION_ID --input '{}'

interact

Interact with elements using

@e

refs from snapshot.

Action	Description	Required Fields
`click`	Click element	`ref`
`fill`	Clear and type text	`ref` , `text`
`type`	Type text (no clear)	`text`
`press`	Press key	`text` (e.g., "Enter")
`select`	Select dropdown	`ref` , `text`
`hover`	Hover over element	`ref`
`scroll`	Scroll page	`direction` (up/down)
`back`	Go back in history	-
`wait`	Wait milliseconds	`wait_ms`

bash

undefined

使用快照中的

@e

引用与元素交互。

操作	描述	必填字段
`click`	点击元素	`ref`
`fill`	清空并输入文本	`ref` , `text`
`type`	输入文本（不清空原有内容）	`text`
`press`	按下按键	`text` （例如："Enter"）
`select`	选择下拉选项	`ref` , `text`
`hover`	悬停在元素上	`ref`
`scroll`	滚动页面	`direction` （up/down）
`back`	返回历史页面	-
`wait`	等待指定毫秒数	`wait_ms`

bash

undefined

Click

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "click", "ref": "@e5" }'

Fill input

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "fill", "ref": "@e1", "text": "hello@example.com" }'

Press Enter

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "press", "text": "Enter" }'

Scroll down

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "scroll", "direction": "down" }'

undefined

infsh app run agentic-browser --function interact --session $SESSION_ID --input '{ "action": "scroll", "direction": "down" }'

undefined

screenshot

Take page screenshot.

bash

infsh app run agentic-browser --function screenshot --session $SESSION_ID --input '{
  "full_page": true
}'

截取页面截图。

bash

infsh app run agentic-browser --function screenshot --session $SESSION_ID --input '{
  "full_page": true
}'

execute

Run JavaScript on the page.

bash

infsh app run agentic-browser --function execute --session $SESSION_ID --input '{
  "code": "document.title"
}'

在页面上运行JavaScript代码。

bash

infsh app run agentic-browser --function execute --session $SESSION_ID --input '{
  "code": "document.title"
}'

close

Close browser session.

bash

infsh app run agentic-browser --function close --session $SESSION_ID --input '{}'

关闭浏览器会话。

bash

infsh app run agentic-browser --function close --session $SESSION_ID --input '{}'

Element Refs

元素引用

Elements are returned with

@e

refs like:

@e1 [a] "Home" href="/"
@e2 [input type="text"] placeholder="Search"
@e3 [button] "Submit"
@e4 [select] "Choose option"

Important: Refs are invalidated after navigation. Always re-snapshot after:

Clicking links/buttons that navigate
Form submissions
Dynamic content loading

元素会以

@e

引用的形式返回，例如：

@e1 [a] "Home" href="/"
@e2 [input type="text"] placeholder="Search"
@e3 [button] "Submit"
@e4 [select] "Choose option"

重要提示：导航后引用会失效。在以下操作后务必重新获取快照：

点击会触发导航的链接/按钮
表单提交
动态内容加载

Examples

示例

Form Submission

表单提交

bash

SESSION=$(infsh app run agentic-browser --function open --session new --input '{
  "url": "https://example.com/contact"
}' | jq -r '.session_id')

bash

SESSION=$(infsh app run agentic-browser --function open --session new --input '{
  "url": "https://example.com/contact"
}' | jq -r '.session_id')

Get elements: @e1 [input] "Name", @e2 [input] "Email", @e3 [textarea] "Message", @e4 [button] "Send"

infsh app run agentic-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e1", "text": "John Doe"}' infsh app run agentic-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e2", "text": "john@example.com"}' infsh app run agentic-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e3", "text": "Hello!"}' infsh app run agentic-browser --function interact --session $SESSION --input '{"action": "click", "ref": "@e4"}'

Check result

infsh app run agentic-browser --function snapshot --session $SESSION --input '{}'

infsh app run agentic-browser --function close --session $SESSION --input '{}'

undefined

infsh app run agentic-browser --function snapshot --session $SESSION --input '{}'

infsh app run agentic-browser --function close --session $SESSION --input '{}'

undefined

Search and Extract

搜索与提取

bash

SESSION=$(infsh app run agentic-browser --function open --session new --input '{
  "url": "https://google.com"
}' | jq -r '.session_id')

bash

SESSION=$(infsh app run agentic-browser --function open --session new --input '{
  "url": "https://google.com"
}' | jq -r '.session_id')

Fill search box and submit

infsh app run agentic-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e1", "text": "weather today"}' infsh app run agentic-browser --function interact --session $SESSION --input '{"action": "press", "text": "Enter"}' infsh app run agentic-browser --function interact --session $SESSION --input '{"action": "wait", "wait_ms": 2000}'

Get results page

infsh app run agentic-browser --function snapshot --session $SESSION --input '{}'

infsh app run agentic-browser --function close --session $SESSION --input '{}'

undefined

infsh app run agentic-browser --function snapshot --session $SESSION --input '{}'

infsh app run agentic-browser --function close --session $SESSION --input '{}'

undefined

Extract Data with JavaScript

使用JavaScript提取数据

bash

infsh app run agentic-browser --function execute --session $SESSION --input '{
  "code": "Array.from(document.querySelectorAll(\"h2\")).map(h => h.textContent)"
}'

bash

infsh app run agentic-browser --function execute --session $SESSION --input '{
  "code": "Array.from(document.querySelectorAll(\"h2\")).map(h => h.textContent)"
}'

Sessions

会话

Browser state persists within a session. Always:

Start with
```
--session new
```
on first call
Use returned
```
session_id
```
for subsequent calls
Close session when done

浏览器状态会在会话中持久化。请始终遵循以下步骤：

首次调用时使用
```
--session new
```
启动会话
后续调用使用返回的
```
session_id
```
使用完成后关闭会话

Related Skills

Web search (for research + browse)

npx skills add inference-sh/skills@web-search

LLM models (analyze extracted content)

npx skills add inference-sh/skills@llm-models

undefined

npx skills add inference-sh/skills@llm-models

undefined

Documentation

文档

inference.sh Sessions - Session management
Multi-function Apps - How functions work

inference.sh Sessions - 会话管理
Multi-function Apps - 函数工作机制

agentic-browser

Original

Translation

Agentic Browser

Agentic Browser

Quick Start

快速开始

Open a page and get interactive elements

Open a page and get interactive elements

Core Workflow

核心工作流

Start session

Start session

Elements returned like: @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Sign In"

Elements returned like: @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Sign In"

Fill form

Fill form

Click submit

Click submit

Close when done

Close when done

Functions

功能函数

open

open

snapshot

snapshot

interact

interact

Click

Click

Fill input

Fill input

Press Enter

Press Enter

Scroll down

Scroll down

screenshot

screenshot

execute

execute

close

close

Element Refs

元素引用

Examples

示例

Form Submission

表单提交

Get elements: @e1 [input] "Name", @e2 [input] "Email", @e3 [textarea] "Message", @e4 [button] "Send"

Get elements: @e1 [input] "Name", @e2 [input] "Email", @e3 [textarea] "Message", @e4 [button] "Send"

Check result

Check result

Search and Extract

搜索与提取

Fill search box and submit

Fill search box and submit

Get results page

Get results page

Extract Data with JavaScript

使用JavaScript提取数据

Sessions

会话

Related Skills

相关技能

Web search (for research + browse)

Web search (for research + browse)

LLM models (analyze extracted content)

LLM models (analyze extracted content)

Documentation

文档