browser-agent-py — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by oxylabs · Agent Tool · ★ 1.6k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is browser-agent-py safe to install? View the security audit →

About browser-agent-py

Browser Agent Browser Agent is an AI browser automation tool from Oxylabs AI Studio. It simulates real user browsing by executing multi-step actions like clicking links, filling forms, scrolling, capturing screenshots, and then extracting structured data – all controlled through natural language prompts. Unlike traditional automation frameworks (e.g., Puppeteer or Selenium), Browser Agent requires no static scraping rules or manual scripting. Users can describe tasks in plain English or provide a sequence of steps, and the AI will carry them out just like a human would. Key features Full control through browser AI – execute clicks, inputs, navigation, and scrolling. Multi-step task execution – define browsing flows in natural language. Multiple outputs – get results in JSON, Markdo

ai-agentai-agentsai-browserai-studiobrowser-agentbrowser-aibrowser-automationbrowser-automation-studio

Quick Facts

Stars1,565
Forks2
CategoryAgent Tool
Quality Score70.9806410415285/100
Last Updated2026-04-02
Created2025-10-13
Platformsbrowser
Est. Tokens~65k

Compatible Skills

These tools work well together with browser-agent-py for enhanced workflows:

  • browser-operator-core — semantic(0.45)+complementary+rare_topics+similar_pop+shared_platform (55%)
  • AIPex — semantic(0.45)+complementary+similar_pop+shared_platform (51%)
  • fetcher-mcp — semantic(0.24)+complementary+similar_pop+shared_platform (48%)
  • open-chatgpt-atlas — semantic(0.25)+complementary+rare_topics+similar_pop+shared_platform (48%)
  • mcp-server-browserbase — semantic(0.35)+complementary+similar_pop+shared_platform (47%)

browser-agent-py alternative? Top 6 similar tools

Looking for a browser-agent-py alternative? If you're comparing browser-agent-py with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • webbrain by webbrain-one · ⭐ 1.2k

    Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

  • oya-browser by OyadotAI · ⭐ 349

    The browser control plane for AI agents. One API over Oya Cloud, Browserbase, Steel, Anchor, Browser Use and y

  • bux by browser-use · ⭐ 419

    Browser Use Box: a 24/7 Claude Code agent for Playwright-style browser automation with Browser Use Cloud, Tele

  • steel-browser by steel-dev · ⭐ 7.7k

    🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that le

  • brightdata-mcp by brightdata · ⭐ 2.6k

    A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.

  • awesome-web-agents by steel-dev · ⭐ 1.5k

    🔥 A list of tools, frameworks, and resources for building AI web agents

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Frequently Asked Questions

What is browser-agent-py?

browser-agent-py is AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.. It is categorized as a Agent Tool with 1.6k GitHub stars.

How do I install or use browser-agent-py?

You can find installation instructions and usage details in the browser-agent-py GitHub repository at github.com/oxylabs/browser-agent-py. The project has 1.6k stars and 2 forks, indicating an active community.

What are the best alternatives to browser-agent-py?

The top alternatives to browser-agent-py on Agent Skills Hub include webbrain, oya-browser, bux. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools