by The-AIOS · MCP Server · ★ 77
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: reads agent memory. 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.
| Stars | 77 |
| Forks | 22 |
| Language | Shell |
| Category | MCP Server |
| License | GPL-2.0 |
| Quality Score | 57/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-17 |
| Created | 2026-05-21 |
| Platforms | claude-code, cli, mcp |
| Est. Tokens | ~16k |
The AIOS — AI as a Team, Not a Tool Everyone is building an AIOS. We built The AIOS. Deciding whether to grant this access to your machine? Read — what each surface can reach and whose identity it acts as, stated without euphemism. If a term there is unfamiliar, defines it in one sentence.
Looking for a aios alternative? If you're comparing aios with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The original AI Chief of Staff built on Claude Code and Obsidian. ADHD prosthetic, open to anyone. Superseded
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
How I turned Claude Code into a persistent AI chief of staff — the full architecture, now installable as a plu
An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vaul
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Harness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Co
Explore other popular mcp server tools:
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: