frago — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 tsaijamey · Agent Tool · ★ 115

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

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

About frago

frago An operating system for AI agents — frago runs AI agents on your computer so you don't have to do repetitive work yourself. frago is not affiliated with OpenClaw. frago predates OpenClaw by approximately one month. 简体中文 Why frago Easy to install, easy to set up. The desktop app is 2MB. After download, it automatically checks and installs everything it needs. Configure one AI model, and you're ready to go. No terminal, no environment setup, no dependencies to manage yourself. You spend hours every day on tasks a computer could do for you — filling spreadsheets, pulling data from websites, moving files around. AI agents can already do these things, but they're trapped behind terminals and command lines that most people can't use. frago gives AI agents a place to run, and gives you a window to watch and control them. Describe what you need, and frago handles the rest. When AI figures out how to do something, frago saves the working steps so the same task can be done again with one click — no AI needed. Get Started Download and install: | Linux (rpm)

aiai-agentsautomationbrowser-automationcdpchrome-automationchrome-devtools-protocolclaude-aiclaude-codeclaude-cowork

Quick Facts

Stars115
Forks19
LanguagePython
CategoryAgent Tool
LicenseAGPL-3.0
Quality Score61.3325820979/100
Open Issues8
Last Updated2026-09-23
Created2025-11-15
Platformsbrowser, claude-code, cli, python
Est. Tokens~14k

frago alternative? Top 6 similar tools

Looking for a frago alternative? If you're comparing frago 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.

  • open-browser-use by iFurySt · ⭐ 311

    🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simp

  • Uni-CLI by olo-dot-io · ⭐ 270

    One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local

  • browser-debugger-cli by szymdzum · ⭐ 148

    CLI tool for agents to quickly access browser telemetry (DOM, network, console) via Chrome DevTools Protocol.

  • notebooklm-ai-plugin by proyecto26 · ⭐ 63

    AI Agent plugin for Google NotebookLM (Claude, OpenClaw, etc) — generate slide decks, audio overviews, videos,

  • daymon by daymonio · ⭐ 365

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • moai-cowork by modu-ai · ⭐ 302

    비개발자를 위한 한국 실무 AI 코워커 패밀리 — Claude Cowork·ChatGPT Work에서 /project 한 번으로 시작

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is frago?

frago is Multi-runtime automation infrastructure for AI agents. Native CDP browser control, metadata-driven Recipe system, and persistent Run context management.. It is categorized as a Agent Tool with 115 GitHub stars.

What programming language is frago written in?

frago is primarily written in Python. It covers topics such as ai, ai-agents, automation.

How do I install or use frago?

You can find installation instructions and usage details in the frago GitHub repository at github.com/tsaijamey/frago. The project has 115 stars and 19 forks, indicating an active community.

What license does frago use?

frago is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to frago?

The top alternatives to frago on Agent Skills Hub include open-browser-use, Uni-CLI, browser-debugger-cli. 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