rome — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 rome-os · Codex Skill · ★ 513

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

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

About rome

Rome The agentic OS for humans and agents. Website · Try Rome Cloud · Documentation · App Store What is Rome? Most progress in AI comes from scaling models. Rome scales the other axis, the environment: the tools, workflows, memory, and interfaces an agent works within (why this matters). Rome is a guardrailed environment where human and agent collaborate, and the collaboration compounds. Agents build their own harnesses, design thei

agentagent-osai-agentai-assistantclaude-codecodexgrok-bot-alternativellmmuse-alternativeopen-source

Quick Facts

Stars513
Forks40
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score63.2714944349106/100
Open Issues63
Last Updated2026-09-20
Created2026-08-23
Platformsclaude-code, codex, node
Est. Tokens~17k

Compatible Skills

These tools work well together with rome for enhanced workflows:

  • nuwax — semantic(0.41)+complementary+rare_topics+same_lang+similar_pop+shared_platform (69%)

rome alternative? Top 6 similar tools

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

  • gawkbot by najmuzzaman-mohammad · ⭐ 1.4k

    open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the

  • avibe by avibe-bot · ⭐ 506

    The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex &

  • natively-cluely-ai-assistant by evinjohnn · ⭐ 877

    Natively - Free open-source AI interview copilot & meeting assistant. The best Cluely alternative, Final Round

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • ai-agent-automation by vmDeshpande · ⭐ 178

    Modular AI agent workflow automation platform with schedulers, tools, and observability. https://vmdeshpande.g

  • Claude-Code-Workflow by catlog22 · ⭐ 2.1k

    JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is rome?

rome is A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse.. It is categorized as a Codex Skill with 513 GitHub stars.

What programming language is rome written in?

rome is primarily written in TypeScript. It covers topics such as agent, agent-os, ai-agent.

How do I install or use rome?

You can find installation instructions and usage details in the rome GitHub repository at github.com/rome-os/rome. The project has 513 stars and 40 forks, indicating an active community.

What license does rome use?

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

What are the best alternatives to rome?

The top alternatives to rome on Agent Skills Hub include gawkbot, avibe, natively-cluely-ai-assistant. 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