Agentshire — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 Agentshire · Codex Skill · ★ 1.3k

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

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

About Agentshire

Agentshire English | 中文 Agentshire — Let your OpenClaw/QClaw agents live in a game town you built yourself, not a ChatBox. Agentshire is an OpenClaw/QClaw plugin that turns AI agents into living NPCs inside a 3D town you can watch, chat with, and shape yourself. It combines a living simulation layer with UGC tools: weather, day/night cycles, social NPCs, a map editor, and a character workshop. Works with both OpenClaw CLI and QClaw desktop app. Vision | Roadmap Compatibility See Troubleshooting for version-specific issues. See It in Action 📺 Watch the full demo on YouTube A town, not a chatbox. https://github.com/user-attachments/assets/c888d2ef-dcba-4caa-b0af-9b5f3e3b1365 Build your characters — pick a model, give them a soul, watch them come alive. https://github.com/user-attachments/assets/b9697432-b3ba-4e23-85fe-4c0b5c35a1b9 Build your town — drag, drop, preview. https://github.com/user-attachments/assets/3328aa6c-3432-4f71-abfd-91aea4db15df Every citizen has a mind of their own. https://github.com/use

3dai-agentsgamedevmulti-agentsopenclawqclawsimulationugcvisualizations

Quick Facts

Stars1,269
Forks197
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score70.1965535286711/100
Open Issues7
Last Updated2026-04-15
Created2026-03-19
Platformsnode
Est. Tokens~1049k

Agentshire alternative? Top 6 similar tools

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

  • anysearch-skill by anysearch-ai · ⭐ 6.2k

    Unified real-time search engine skill for AI agents. Supports general web search, vertical domain search, para

  • skillshare by runkids · ⭐ 2.8k

    📚 Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

  • Claw3D by iamlukethedev · ⭐ 2.2k

    Claw3D is an open source 3D engine built on OpenClaw for creating games, simulations, and high-performance 3D

  • anysearch-mcp-server by anysearch-ai · ⭐ 1.9k

    Unified real-time search MCP server supporting general web search, vertical domain search, parallel batch sear

  • ai-maestro by 23blocks-OS · ⭐ 817

    AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agen

  • qclaw-wechat-client by photon-hq · ⭐ 798

    Reverse-engineered TypeScript client for QClaw's WeChat Access API.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Agentshire?

Agentshire is OpenClaw / QClaw plugin that visualizes AI agents as 3D NPCs in a game town — with social simulation, a map editor, and a character workshop.. It is categorized as a Codex Skill with 1.3k GitHub stars.

What programming language is Agentshire written in?

Agentshire is primarily written in TypeScript. It covers topics such as 3d, ai-agents, gamedev.

How do I install or use Agentshire?

You can find installation instructions and usage details in the Agentshire GitHub repository at github.com/Agentshire/Agentshire. The project has 1.3k stars and 197 forks, indicating an active community.

What license does Agentshire use?

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

What are the best alternatives to Agentshire?

The top alternatives to Agentshire on Agent Skills Hub include anysearch-skill, skillshare, Claw3D. 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