intelli-browser — security grade SAFE, quality 76/100

Security audit verdict: SAFE · quality 76/100

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 lvqq · Agent Tool · ★ 51

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

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

About intelli-browser

Intelli-Browser Introduction Use natural language to control your browser, powered by LLM and playwright Features ✨ Use natural language to write and run e2e test cases 🧪 Generate traditional e2e test cases after executing the cases 💭 More feautes are coming soon! Feel free to open an issue or submit a pull request Demo MDN Demo Video User Task Click search and input "Web API", press "arrow down" once to select the second result. Then press "ENTER" to search it. Find "Keyboard API" nearby title "K" and click it Limitaions Only claude-3-5-sonnet LLM is supported for now Only playwright framework is supported for now Requirement NodeJS = 18 Usage Example The example is under directory , try the following steps to have an experience: bash clone the repository git clone https://github.com/lvqq/intelli-browser.git install dependencies and browsers pnpm i build all packages pnpm -r build add your ANTHROPICAPIKEY run demo pnpm run de

anthropicclaudeclaude-3-5-sonnetcomputer-usee2ee2e-testsplaywright

Quick Facts

Stars51
Forks4
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score76.3269474722455/100
Last Updated2024-11-16
Created2024-11-08
Platformsbrowser, claude-code, node
Est. Tokens~692k

intelli-browser alternative? Top 6 similar tools

Looking for a intelli-browser alternative? If you're comparing intelli-browser 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.

  • os-ai-computer-use by 777genius · ⭐ 176

    AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app

  • glance by DebugBase · ⭐ 156

    AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your te

  • claude-ai-toolkit by ramonclaudio · ⭐ 60

    A lightweight Python CLI for Anthropic’s Claude language models.

  • factif-ai by presidio-oss · ⭐ 56

    AI-powered computer control for automated testing. Factifai uses vision models (Claude, GPT-4o, Gemini) to int

  • claudex by Mng-dev-ai · ⭐ 224

    Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is intelli-browser?

intelli-browser is ✨ Use natural language to control your browser, powered by LLM and playwright. It is categorized as a Agent Tool with 51 GitHub stars.

What programming language is intelli-browser written in?

intelli-browser is primarily written in TypeScript. It covers topics such as anthropic, claude, claude-3-5-sonnet.

How do I install or use intelli-browser?

You can find installation instructions and usage details in the intelli-browser GitHub repository at github.com/lvqq/intelli-browser. The project has 51 stars and 4 forks, indicating an active community.

What license does intelli-browser use?

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

What are the best alternatives to intelli-browser?

The top alternatives to intelli-browser on Agent Skills Hub include os-ai-computer-use, glance, claude-ai-toolkit. 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