Hermuse: Hermuse — personal AI agent stack built for Muse: Hermes + 9Router + Telegram gateway, automated install

Security audit verdict: CAUTION · quality 70/100

Flagged: installs a cron job, sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

About Hermuse

Hermuse — self-hosted AI agent stack (Hermes + 9Router + Telegram) 🇬🇧 English · 🇮🇩 Indonesia · 🇲🇾 Malaysia · 🇻🇳 Việt Nam · 🇮🇳 हिन्दी · 🇯🇵 日本語 [![Cloudflare](https://img.shields.io/badge/Cloudflare-Tunnel-F68204?sty

Compatible Skills

These tools work well together with Hermuse for enhanced workflows:

• hermes-agent-control-room — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
• Hermes-Agent-On-Android — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
• ai-coding-primer — semantic(0.16)+complementary+shared_fw(cloudflare)+similar_pop (49%)

Hermuse alternative? Top 6 similar tools

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

• GoGogot by aspasskiy · ⭐ 298

  Lightweight self-hosted AI agent. Open-source OpenClaw alternative in Go.

• ciana-parrot by emanueleielo · ⭐ 77

  Self-hosted AI assistant built on DeepAgents, LangChain and LangGraph: Telegram chat, scheduled tasks, MCP int

• Agenvoy by pardnchiu · ⭐ 532

  A local AI agent harness in Go that runs 24/7 with auto-built tools, MCP, and Ollama

• concierge by concierge-hq · ⭐ 531

  🚀 Universal SDK for building next-gen MCP servers

• openlegion by openlegion-ai · ⭐ 116

  Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate age

• chibi by s-nagaev · ⭐ 55

  Your Digital Companion. Self-hosted Telegram bot orchestrating multiple AI providers (OpenAI, Anthropic, Googl

More Codex Skill Tools

Explore other popular codex skill tools:

• superset ⭐ 15.6k
• humanizer ⭐ 57.5k
• refly ⭐ 7.5k
• nano-banana-pro-prompts-recommend-skill ⭐ 1.9k
• pi-skills ⭐ 2.5k
• skillkit ⭐ 1.5k
• ai-maestro ⭐ 835
• upskill ⭐ 762
• Claude-to-IM-skill ⭐ 2.9k
• learning-opportunities ⭐ 2.4k

Popular Shell Agent Tools

• mcp-server-bash-sdk ⭐ 515 · MCP Server
• Claude-Code-Development-Kit ⭐ 1.4k · MCP Server
• claude-init ⭐ 1.4k · MCP Server
• claude-code-mastery ⭐ 548 · MCP Server
• claude-code-statusline ⭐ 477 · MCP Server

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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:

• SlowMist agent-security taxonomy
• Liu et al., An Empirical Study of Agent Skill Security (2026)
• Our census dataset (DOI 10.5281/zenodo.21292799) · Hugging Face mirror
• How we grade: all 42 rules, the source tiers and known limits
• Full methodology & who runs this