AgentHub — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Stanshy · Agent Tool · ★ 200

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

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

About AgentHub

AgentHub One Person, One Software Company. Build a virtual development team with Claude Code, and use Harness Engineering to keep AI working with discipline. Website · Claude Code Mastery · Quick Start English | 繁體中文 AgentHub is not another AI chat interface. It is a Harness Engineering system that lets you build a virtual development team with Claude Code — complete with a PM, Tech Lead, frontend developer, backend developer, and designer — and manage them like a real boss. You give the orders. Agents execute. Hooks enforce quality. Skills standardize process. FileWatcher syncs in real time. No prompt prayers. No "hope the AI remembers the rules." Rules live in Hooks. Agents that break them get blocked. It's that simple.

ai-agentsai-workflowclaude-codedeveloper-toolselectronharness-engineeringopen-sourceteam-managementtypescriptvue

Quick Facts

Stars200
Forks23
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score67.1308888481703/100
Open Issues1
Last Updated2026-04-09
Created2026-03-27
Platformsclaude-code, node
Est. Tokens~226k

Compatible Skills

These tools work well together with AgentHub for enhanced workflows:

  • mcp-gearbox — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)

AgentHub alternative? Top 6 similar tools

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

  • claude_agent_teams_ui by 777genius · ⭐ 868

    You're the CTO, agents are your team. They handle tasks on their own, message each other, and review each othe

  • mcp-gearbox by rohitsoni007 · ⭐ 62

    A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents

  • Carmack-Council by SamJHudson01 · ⭐ 51

    Multi-agent Claude Code skill for building apps and stuff

  • daymon by daymonio · ⭐ 365

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • Claude-Agent-Team-Manager by DatafyingTech · ⭐ 140

    Visual org-chart desktop app for managing Claude Code agent teams, skills, and configurations

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is AgentHub?

AgentHub is One person, one software company. Manage 47 AI agents from a single Electron app — with Harness Engineering (Skills + Hooks + FileWatchers) for disciplined, traceable AI workflows.. It is categorized as a Agent Tool with 200 GitHub stars.

What programming language is AgentHub written in?

AgentHub is primarily written in TypeScript. It covers topics such as ai-agents, ai-workflow, claude-code.

How do I install or use AgentHub?

You can find installation instructions and usage details in the AgentHub GitHub repository at github.com/Stanshy/AgentHub. The project has 200 stars and 23 forks, indicating an active community.

What license does AgentHub use?

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

What are the best alternatives to AgentHub?

The top alternatives to AgentHub on Agent Skills Hub include claude_agent_teams_ui, mcp-gearbox, Carmack-Council. 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