LinkWork — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 momotech · MCP Server · ★ 116

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

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

About LinkWork

LinkWork (灵工) 🤖 Make AI Work Like Your Team Open-source enterprise AI workforce platform — Roles · Skills · Tools · Security · Scheduling, all in one place English | 中文 Introduction LinkWork is an open-source enterprise AI Agent platform. It does not just make AI "answer", it makes AI "deliver". You can manage containerized AI employees at scale and govern roles, Skills, MCP tools, and security policies with declarative configuration. From task orchestration to result delivery, LinkWork turns AI workflows into a standardized production line: orchestratable, observable, auditable, and reusable. It is not a personal assistant. It is an AI team operating system built for organizational collaboration. Features ⚡ Fast to Launch: From "Using AI" to "Using AI Well" Role template management — Define responsibilities, persona, available Skills, and tool permissions in one place, then instantiate and run Contai

agent-frameworkai-agentsai-automationai-platformai-workersai-workforceenterprise-aiharnessharness-engineeringkubernetes

Quick Facts

Stars116
Forks14
LanguageDockerfile
CategoryMCP Server
LicenseApache-2.0
Quality Score63.4858718732674/100
Open Issues4
Last Updated2026-03-31
Created2026-03-16
Platformsk8s, mcp
Est. Tokens~1008k

LinkWork alternative? Top 6 similar tools

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

  • openacme by sandydasari · ⭐ 85

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

  • plumoai by PlumoAI · ⭐ 67

    World's First Autonomous Open-source Pretrained AI Employees Platform

  • squads-cli by agents-squads · ⭐ 51

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

  • aeon by aaronjmars · ⭐ 573

    The most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever.

  • EDDI by labsai · ⭐ 376

    Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM provi

  • omnicoreagent by omnirexflora-labs · ⭐ 246

    Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, backgro

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Dockerfile Agent Tools

Frequently Asked Questions

What is LinkWork?

LinkWork is Open-source enterprise AI workforce platform — containerized roles, declarative skills, MCP tools, policy-driven security, K8s-native scheduling. It is categorized as a MCP Server with 116 GitHub stars.

What programming language is LinkWork written in?

LinkWork is primarily written in Dockerfile. It covers topics such as agent-framework, ai-agents, ai-automation.

How do I install or use LinkWork?

You can find installation instructions and usage details in the LinkWork GitHub repository at github.com/momotech/LinkWork. The project has 116 stars and 14 forks, indicating an active community.

What license does LinkWork use?

LinkWork 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 LinkWork?

The top alternatives to LinkWork on Agent Skills Hub include openacme, plumoai, squads-cli. 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