agentos — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 iii-experimental · MCP Server · ★ 163

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

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

About agentos

website · architecture · quickstart · workers § 01 · Thesis AgentOS isn't another agent framework. It's what's left when the runtime becomes someone else's problem. 65 narrow workers — one Rust binary per domain — register Functions and Triggers on the iii engine. Every capability is one shape: . The engine carries r

agent-frameworkai-agentiii-enginellmmcpmulti-agentorchestrationrustself-evolvingtypescript

Quick Facts

Stars163
Forks24
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score68.2967660881511/100
Open Issues4
Last Updated2026-05-07
Created2026-03-01
Platformsmcp, node
Est. Tokens~94k

Compatible Skills

These tools work well together with agentos for enhanced workflows:

  • agentos — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (69%)
  • AgenticFORGE — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (54%)
  • metabot — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • cube-pets-office — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • godmode — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (52%)

agentos alternative? Top 6 similar tools

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

  • agentos by iii-hq · ⭐ 104

    The agent OS that evolves itself. 51 workers, 18 security layers, self-improving functions. Built on iii-engin

  • awesome-agent-evolution by EvoMap · ⭐ 229

    A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects

  • dexto by truffle-ai · ⭐ 651

    Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • openclaw.net by clawdotnet · ⭐ 479

    Self-hosted OpenClaw gateway + agent runtime in .NET (NativeAOT-friendly)

  • aser by AmeNetwork · ⭐ 472

    Aser is a lightweight, self-assembling AI Agent frame.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is agentos?

agentos is The agent OS that evolves itself. 51 workers, 18 security layers, self-improving functions. Built on iii-engine.. It is categorized as a MCP Server with 163 GitHub stars.

What programming language is agentos written in?

agentos is primarily written in TypeScript. It covers topics such as agent-framework, ai-agent, iii-engine.

How do I install or use agentos?

You can find installation instructions and usage details in the agentos GitHub repository at github.com/iii-experimental/agentos. The project has 163 stars and 24 forks, indicating an active community.

What license does agentos use?

agentos is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to agentos?

The top alternatives to agentos on Agent Skills Hub include agentos, awesome-agent-evolution, dexto. 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 MCP Server tools