Abu-Cowork: Open-source AI office assistant for your desktop: describe the result or file you want in one sentence

by PM-Shawn · MCP Server · ★ 421

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

How to install Abu-Cowork

git clone https://github.com/PM-Shawn/Abu-Cowork.git

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 65/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

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.

agent-frameworkagentic-aiai-agentai-assistantai-office-assistantautomationclaude-coworkdeepseekdesktop-appdesktop-automation

Quick Facts

Stars421
Forks100
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score65/100
Open Issues138
Last Updated2026-11-13
Created2026-03-09
Platformsclaude-code, mcp, node
Est. Tokens~17k

About Abu-Cowork

中文 | English Abu (阿布) 你的 AI 桌面办公搭子 — 交给阿布就行啦 本地运行的 AI 桌面办公助手,灵感来自 Claude Code 的 Cowork 模式。 你说需求,阿布干活 — 读文件、跑命令、写文档、做报表,全在本地完成。 下载安装 · 快速开始 · 功能介绍 · 使用指南 · 从源码构建 为什么选择 Abu? 最近更新 v0.16 — 用量统计改版:热力图 + 自定义 Tooltip,按模型 / 技能分维度查看 Token 用量;设置页独占视图:设置、自动化、工具箱改为全屏视图,不再挤在侧边栏;诊断包导出完整落地(v0.16.1);AI 服务健康检查错误信息透传(v0.16.2) v0.15 — 性格系统(Soul):主动度三档预设(寡言 / 伙伴

Compatible Skills

These tools work well together with Abu-Cowork for enhanced workflows:

  • PII-Shield — semantic(0.50)+complementary+same_lang+similar_pop+shared_platform (63%)
  • relay — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (55%)

Abu-Cowork alternative? Top 6 similar tools

Looking for a Abu-Cowork alternative? If you're comparing Abu-Cowork 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.

  • Sentient by existence-master · ⭐ 719

    Your personal AI assistant, running on your own computer. Long-running tasks, real memory, proactive help, voi

  • dsh-desktop by vibeinging · ⭐ 495

    DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, pl

  • deepseek-harness-desktop-app by vibeinging · ⭐ 115

    DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, pl

  • py-gpt by szczyglis-dev · ⭐ 2.0k

    Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Grok, Ollama, DeepSeek, Perplexity, and more - c

  • Overture by SixHq · ⭐ 642

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

  • openclaw-desktop by rshodoskar-star · ⭐ 120

    🖥️ A native desktop client for OpenClaw premium UI experience without the browser. Built with Electron + Rea

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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:

View on GitHub → Browse MCP Server tools