Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by rexlunae · Codex Skill · ★ 60
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is RustyClaw safe to install? View the security audit →
RustyClaw 🦀🦞 The secure, open-source operating system for AI agents Quick Start • Building • Why RustyClaw • Features • Security • Architecture What is RustyClaw? RustyClaw is an agentic AI operating system — a complete runtime for deploying, orchestrating, and securing AI agents. It provides everything agents need: tools, memory, isolation, scheduling, multi-agent coordination, and secure credential management. Think of it as Linux for AI agents: a stable, secure foundation that han
| Stars | 60 |
| Forks | 14 |
| Language | Rust |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 69.7238306897131/100 |
| Open Issues | 15 |
| Last Updated | 2026-09-30 |
| Created | 2026-02-11 |
| Platforms | rust |
| Est. Tokens | ~26k |
Looking for a RustyClaw alternative? If you're comparing RustyClaw with other codex skill tools, these 1 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Codex/Claude skill that maintains per-repo operating theory documents.
Explore other popular codex skill tools:
RustyClaw is A super-lightweight super-capable agentic tool with improved security versus OpenClaw.. It is categorized as a Codex Skill with 60 GitHub stars.
RustyClaw is primarily written in Rust.
You can find installation instructions and usage details in the RustyClaw GitHub repository at github.com/rexlunae/RustyClaw. The project has 60 stars and 14 forks, indicating an active community.
RustyClaw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to RustyClaw on Agent Skills Hub include theorist. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: