markus — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 markus-global · Agent Tool · ★ 195

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

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

About markus

Markus Build AI teams that actually deliver. The open-source AI workforce platform. Developers, researchers, writers, analysts &mdash; an AI team that runs around the clock at a fraction of the cost. Website &middot; Blog &middot; Docs &middot; <a href="https:/

agent-governanceagent-orchestrationagent-platformagent-runtimeagent-to-agentagentic-aiai-agentsai-automationai-companyai-employees

Quick Facts

Stars195
Forks13
LanguageTypeScript
CategoryAgent Tool
LicenseApache-2.0
Quality Score68.8590127859483/100
Open Issues7
Last Updated2026-09-23
Created2026-03-19
Platformsnode
Est. Tokens~16k

Compatible Skills

These tools work well together with markus for enhanced workflows:

  • squads-cli — semantic(0.32)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • openteams — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)

markus alternative? Top 6 similar tools

Looking for a markus alternative? If you're comparing markus with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • 5dive by 5dive-ai · ⭐ 60

    Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org

  • openhermit by HCF-STUDIOS · ⭐ 84

    OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable stat

  • ai-maestro by 23blocks-OS · ⭐ 792

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

  • openacme by sandydasari · ⭐ 85

    An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You

  • squads-cli by agents-squads · ⭐ 53

    CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.

  • awesome-openclaw by SamurAIGPT · ⭐ 957

    A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdb

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is markus?

markus is The all-in-one AI workforce platform, to build AI agent teams. You are the boss.. It is categorized as a Agent Tool with 195 GitHub stars.

What programming language is markus written in?

markus is primarily written in TypeScript. It covers topics such as agent-governance, agent-orchestration, agent-platform.

How do I install or use markus?

You can find installation instructions and usage details in the markus GitHub repository at github.com/markus-global/markus. The project has 195 stars and 13 forks, indicating an active community.

What license does markus use?

markus 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 markus?

The top alternatives to markus on Agent Skills Hub include 5dive, openhermit, ai-maestro. 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 Agent Tool tools