ego-lite — 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 citrolabs · Codex Skill · ★ 16.4k

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

🔒 Is ego-lite safe to install? View the security audit →

About ego-lite

The best browser for both you and your AI agents work in parallel. ego (lite) is a browser where you and your AI agents work in parallel. Your agents run multiple browser tasks in their own Spaces while your tabs stay yours, and tasks complete faster on fewer tokens. Existing tools like browser-use and agent-br

agent-skillsai-agentautomationbrowserbrowser-automationclaude-codecodexhermes-agentskillsskills-sh

Quick Facts

Stars16,426
Forks872
LanguageJavaScript
CategoryCodex Skill
LicenseMIT
Quality Score68.7365810634929/100
Open Issues170
Last Updated2026-09-23
Created2026-04-16
Platformsbrowser, claude-code, codex, node
Est. Tokens~15k

Compatible Skills

These tools work well together with ego-lite for enhanced workflows:

  • solana-dev-skill — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • getdesign — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)

ego-lite alternative? Top 6 similar tools

Looking for a ego-lite alternative? If you're comparing ego-lite 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.

  • cherry-studio by CherryHQ · ⭐ 52.3k

    AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLM

  • awesome-claude-skills by ComposioHQ · ⭐ 75.3k

    A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

  • refly by refly-ai · ⭐ 7.5k

    The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex

  • humanizer by blader · ⭐ 52.7k

    Agent skill that removes signs of AI-generated writing from text

  • awesome-agent-skills by VoltAgent · ⭐ 35.1k

    A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude C

  • planning-with-files by OthmanAdi · ⭐ 27.2k

    Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, sessio

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is ego-lite?

ego-lite is The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero conf. It is categorized as a Codex Skill with 16.4k GitHub stars.

What programming language is ego-lite written in?

ego-lite is primarily written in JavaScript. It covers topics such as agent-skills, ai-agent, automation.

How do I install or use ego-lite?

You can find installation instructions and usage details in the ego-lite GitHub repository at github.com/citrolabs/ego-lite. The project has 16.4k stars and 872 forks, indicating an active community.

What license does ego-lite use?

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

What are the best alternatives to ego-lite?

The top alternatives to ego-lite on Agent Skills Hub include cherry-studio, awesome-claude-skills, refly. 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