stagehand — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 browserbase · Codex Skill · ★ 25.5k

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

🔒 Is stagehand safe to install? View the security audit →

Featured in: browser-use, Playwright MCP & AI Browser Agents

About stagehand

The AI Browser Automation Framework Read the Docs <p align="c

agentsaiai-agentsbrowser-agentbrowser-automationcdpcloud-browserdata-extractionheadless-chromeplaywright

Quick Facts

Stars25,524
Forks1,752
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score68.5009273072234/100
Open Issues378
Last Updated2026-10-02
Created2024-03-24
Platformsbrowser, claude-code, codex, node
Est. Tokens~15k

Compatible Skills

These tools work well together with stagehand for enhanced workflows:

  • steel-browser — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • collab-public — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • dev-browser — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • hyperframes — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • playwright-mcp — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)

stagehand alternative? Top 6 similar tools

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

  • Scrapling by D4Vinci · ⭐ 85.4k

    🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Do

  • nanobrowser by nanobrowser · ⭐ 13.9k

    Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API k

  • moli by lexmount · ⭐ 5.5k

    Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust

  • browser-use by browser-use · ⭐ 117.0k

    Agents that use the browser.

  • mcp-agent by lastmile-ai · ⭐ 8.5k

    Build effective agents using Model Context Protocol and simple workflow patterns

  • ruflo by ruvnet · ⭐ 73.8k

    🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and bu

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is stagehand?

stagehand is The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.. It is categorized as a Codex Skill with 25.5k GitHub stars.

What programming language is stagehand written in?

stagehand is primarily written in TypeScript. It covers topics such as agents, ai, ai-agents.

How do I install or use stagehand?

You can find installation instructions and usage details in the stagehand GitHub repository at github.com/browserbase/stagehand. The project has 25.5k stars and 1752 forks, indicating an active community.

What license does stagehand use?

stagehand is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to stagehand?

The top alternatives to stagehand on Agent Skills Hub include Scrapling, nanobrowser, moli. 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 Codex Skill tools