@mastra/core
Version:
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
168 lines (115 loc) • 4.68 kB
Markdown
Browser support enables agents to navigate websites, interact with page elements, fill forms, and extract data. Mastra provides browser capabilities through SDK providers that wrap browser automation libraries and a CLI provider for agents that drive browsers through command-line tools.
Mastra supports two SDK providers and one CLI provider:
- [**AgentBrowser**](https://mastra.ai/docs/browser/agent-browser): A Playwright-based provider with accessibility-first element targeting. Best for general web automation and scraping.
- [**Stagehand**](https://mastra.ai/docs/browser/stagehand): A Browserbase provider with AI-powered element detection. Best for complex interactions that benefit from natural language selectors.
- [**BrowserViewer**](https://mastra.ai/docs/browser/browser-viewer): A CLI provider that launches Chrome and injects CDP URLs into CLI tools like agent-browser, browser-use, and browse. Best for workspace agents that drive browsers through shell commands.
Use browser when your agent needs to:
- Navigate websites and interact with page elements
- Fill out forms and submit data
- Extract structured data from web pages
- Automate multi-step web workflows
- Take actions that require a real browser (JavaScript rendering, authentication flows)
## How it works
When you assign a browser to an agent, Mastra includes the provider's tools in the agent's toolset. The agent uses these tools to control the browser: navigating to URLs, selecting elements, typing text, and reading page content.
Each provider offers a different set of tools optimized for its approach.
## Quickstart
Install your provider of choice, for this example you'll use the AgentBrowser provider.
**npm**:
```bash
npm install @mastra/agent-browser
```
**pnpm**:
```bash
pnpm add @mastra/agent-browser
```
**Yarn**:
```bash
yarn add @mastra/agent-browser
```
**Bun**:
```bash
bun add @mastra/agent-browser
```
Create a new browser instance:
```typescript
import { AgentBrowser } from '@mastra/agent-browser'
export const browser = new AgentBrowser({
headless: false,
})
```
Assign the browser to an agent:
```typescript
import { Agent } from '@mastra/core/agent'
import { browser } from '../browsers'
export const webAgent = new Agent({
id: 'web-agent',
name: 'Web Agent',
description: 'A web automation assistant that can navigate websites and complete tasks.',
model: 'openai/gpt-5.4',
browser,
instructions:
'You are a web automation assistant. Use browser tools to navigate websites and complete tasks.',
})
```
The agent automatically receives all browser tools from the provider.
Both SDK providers support connecting to cloud browser services instead of launching a local browser.
Stagehand has native Browserbase integration:
```typescript
import { StagehandBrowser } from '@mastra/stagehand'
const browser = new StagehandBrowser({
env: 'BROWSERBASE',
apiKey: process.env.BROWSERBASE_API_KEY,
projectId: process.env.BROWSERBASE_PROJECT_ID,
})
```
Connect to any browser exposing a Chrome DevTools Protocol (CDP) endpoint:
```typescript
import { AgentBrowser } from '@mastra/agent-browser'
const browser = new AgentBrowser({
cdpUrl: process.env.BROWSER_CDP_URL,
headless: true,
})
```
This works with any [CDP-compatible](https://chromedevtools.github.io/devtools-protocol/) browser service.
Browser providers stream a live video feed of the browser to the Mastra Studio UI. This lets you watch the agent interact with pages in real-time.
Screencast requires WebSocket support. Install these packages in your project:
**npm**:
```bash
npm install ws @hono/node-ws
```
**pnpm**:
```bash
pnpm add ws @hono/node-ws
```
**Yarn**:
```bash
yarn add ws @hono/node-ws
```
**Bun**:
```bash
bun add ws @hono/node-ws
```
> **Note:** These packages are not included by default because they are incompatible with serverless environments like Cloudflare Workers. If they are not installed, screencast is disabled but all other browser functionality works normally.
Screencast is enabled by default and can be configured:
```typescript
const browser = new AgentBrowser({
screencast: {
enabled: true,
format: 'jpeg',
quality: 80,
maxWidth: 1280,
maxHeight: 720,
},
})
```
- [AgentBrowser](https://mastra.ai/docs/browser/agent-browser)
- [Stagehand](https://mastra.ai/docs/browser/stagehand)
- [BrowserViewer](https://mastra.ai/docs/browser/browser-viewer)
- [MastraBrowser reference](https://mastra.ai/reference/browser/mastra-browser)