Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by eastreams · Codex Skill · ★ 640
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is loong safe to install? View the security audit →
🐉 Loong - Rust Base for Vertical AI Agents "Originated from the East, here to benefit the world" </
| Stars | 640 |
| Forks | 105 |
| Language | Rust |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 63.9250419994617/100 |
| Open Issues | 47 |
| Last Updated | 2026-09-23 |
| Created | 2026-03-05 |
| Platforms | rust |
| Est. Tokens | ~25k |
Looking for a loong alternative? If you're comparing loong 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.
Lightweight, clear, and fully extensible AI agent infrastructure — learn easily, customize anything 🐉
Lightweight coding agent written in Rust, optimized for memory footprint and performance
AI agent microservice
An open-source AI assistant framework with skills and agent architecture
A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonom
ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloa
Explore other popular codex skill tools:
loong is Lightweight, clear, and fully extensible AI agent infrastructure — learn easily, customize anything 🐉. It is categorized as a Codex Skill with 640 GitHub stars.
loong is primarily written in Rust. It covers topics such as agent, agentic-ai, agents.
You can find installation instructions and usage details in the loong GitHub repository at github.com/eastreams/loong. The project has 640 stars and 105 forks, indicating an active community.
loong is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to loong on Agent Skills Hub include loongclaw, zerostack, core. 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: