AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Browser Automation/
browser-agent-py
browser-agent-py logo

browser-agent-py

Active·★ 1.6k·Updated 2026-04-02

`browser-agent-py` is the official Python reference repository and guide for Browser Agent, an AI-driven browser automation application within the `oxylabs-ai-studio` SDK. Instead of writing brittle CSS/XPath selectors or maintaining Playwright/Selenium scripts, developers pass a target URL and a natural-language prompt (or step array) describing clicks, form inputs, scrolling, and extraction goals. The agent executes the multi-step browsing flow on JavaScript-rendered pages and returns the result as structured JSON (validated against an OpenAPI/Pydantic-style schema that can also be auto-generated from a prompt), Markdown, raw HTML, or a base64-encoded PNG screenshot, with optional ISO2 geo-location proxy routing.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#AI Automation#Browser Automation#Web Scraping#Natural Language#Python SDK#Web Browsing#Coding
$ Install
$ pip install oxylabs-ai-studio
↗ Visit site★ GitHub
01

Features

01Full control through browser AI – execute clicks, inputs, navigation, and scrolling.
02Multi-step task execution – define browsing flows in natural language.
03Multiple outputs – get results in JSON, Markdown, HTML, or PNG screenshots.
04Dynamic content support – interact with JavaScript-rendered pages.
05Schema-based extraction – request structured JSON after the browsing sequence completes.
02

Why choose it

+Replaces manual DOM selector maintenance with natural-language browsing prompts and automatic JSON schema generation.
+Outputs clean JSON, Markdown, HTML, or PNG screenshots with built-in geo-location proxy parameter support.
+Simple Python 3.10+ SDK (`oxylabs-ai-studio`) that integrates into data pipelines in a few lines of code.
03

Trade-offs

!Requires an Oxylabs AI Studio API key and consumes commercial cloud credits after the 1,000-credit free trial.
!This repository mainly contains documentation and SDK usage examples rather than a self-hostable local browser engine.
04

Compatibility

Oxylabs AI Studio
Native Support
Verified via docs
Python
Required Python
Verified via docs
05

Quick start

1
$ pip install oxylabs-ai-studio
06

Use cases

↳E-commerce checkout simulation – add items to cart, apply coupon, confirm checkout flow.
↳Travel search automation – enter destinations, apply filters, and extract flight or hotel prices.
↳Job search scraping – search for a role, click through postings, extract job details.
07

Alternatives

⚡Top VS:
VSmcp-chrome★12.5k→VSmcp-playwright★5.7k→VSchrome-devtools-mcp★54.0k→VSmcp★7.2k→
mcp-chrome logo
mcp-chrome★ 12.5k
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
VSCompare→
mcp-playwright logo
mcp-playwright★ 5.7k
Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌
VSCompare→
chrome-devtools-mcp logo
chrome-devtools-mcp★ 54.0k
Chrome DevTools for coding agents
VSCompare→
mcp logo
mcp★ 7.2k
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
VSCompare→
firecrawl-mcp-server logo
firecrawl-mcp-server★ 7.7k
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
VSCompare→
browser-tools-mcp logo
browser-tools-mcp★ 7.3k
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
VSCompare→
playwright-mcp logo
playwright-mcp★ 38.5k
Playwright MCP server
VSCompare→
mcp-server-browserbase logo
mcp-server-browserbase★ 3.4k
Allow LLMs to control a browser with Browserbase and Stagehand
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
oxylabs /
browser-agent-py
↗

Python SDK interface for Oxylabs AI Studio's natural-language browser automation and schema extraction

1.6k
Last commit6mo ago
StatusActive
CategoryBrowser Automation
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.