by PM-Shawn
Claude Cowork 开源替代品,开源的本地 AI Agent 桌面端 · 多模型适配 · 自进化 Skills · 隐私优先
# Add to your Claude Code skills
git clone https://github.com/PM-Shawn/Abu-CoworkLast scanned: 7/5/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@babel/core: @babel/core: Arbitrary File Read via sourceMappingURL Comment",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@hono/node-server: @hono/node-server has authorization bypass for protected static paths via encoded slashes in Serve Static Middleware",
"severity": "high"
},
{
"type": "npm-audit",
"message": "brace-expansion: brace-expansion: Large numeric range defeats documented `max` DoS protection",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "echarts: Apache ECharts has a cross-site scripting (XSS) vulnerability",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "esbuild: esbuild allows arbitrary file read when running the development server on Windows",
"severity": "low"
},
{
"type": "npm-audit",
"message": "express-rate-limit: express-rate-limit: IPv4-mapped IPv6 addresses bypass per-client rate limiting on servers with dual-stack network",
"severity": "high"
},
{
"type": "npm-audit",
"message": "flatted: flatted vulnerable to unbounded recursion DoS in parse() revive phase",
"severity": "high"
},
{
"type": "npm-audit",
"message": "js-yaml: JS-YAML: Quadratic-complexity DoS in merge key handling via repeated aliases",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "lodash: lodash vulnerable to Code Injection via `_.template` imports key names",
"severity": "high"
},
{
"type": "npm-audit",
"message": "path-to-regexp: path-to-regexp vulnerable to Denial of Service via sequential optional groups",
"severity": "high"
},
{
"type": "npm-audit",
"message": "picomatch: Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching",
"severity": "high"
},
{
"type": "npm-audit",
"message": "pptx-preview: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "uuid: uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "xlsx: Prototype Pollution in sheetJS",
"severity": "high"
}
],
"status": "WARNING",
"scannedAt": "2026-07-05T07:24:53.587Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}Abu-Cowork is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by PM-Shawn. Claude Cowork 开源替代品,开源的本地 AI Agent 桌面端 · 多模型适配 · 自进化 Skills · 隐私优先. It has 183 GitHub stars.
Abu-Cowork returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.
Clone the repository with "git clone https://github.com/PM-Shawn/Abu-Cowork" and add it to your Claude Code skills directory (see the Installation section above).
Abu-Cowork is primarily written in TypeScript. It is open-source under PM-Shawn on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Abu-Cowork against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
中文 | English
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
| 特性 | Abu | 普通 AI 聊天 | 传统自动化工具 |
|---|---|---|---|
| 自主规划并执行复杂任务 | :white_check_mark: | :x: | :x: |
| 读写本地文件、执行命令 | :white_check_mark: | :x: | :white_check_mark: |
| 自然语言交互 | :white_check_mark: | :white_check_mark: | :x: |
| 28 个内置技能 + 自进化(阿布自己攒新技能) | :white_check_mark: | :x: | :x: |
| 多对话按项目聚合(Projects) | :white_check_mark: | :x: | :x: |
| 定时任务 & 事件触发 | :white_check_mark: | :x: | :white_check_mark: |
| IM 机器人(飞书/钉钉/企微/Slack) | :white_check_mark: | :x: | 部分 |
| 多 Agent 后台并行 | :white_check_mark: | :x: | :x: |
| 浏览器 & 电脑操控 | :white_check_mark: | :x: | 部分 |
| 数据 100% 本地,隐私安全 | :white_check_mark: | :x: | :white_check_mark: |
最新版本 v0.25.0 — 实验室(Labs)· 桌宠交互升级 · 浅/深/跟随系统主题切换。
近期亮点:实验室(Labs) 实验功能框架(当前收录:桌宠)、桌宠模式 交互升级 + 活动通知条、主题切换(亮色 / 暗色 / 跟随系统)、每对话独立设置(模型固定 + 权限模式随对话切换)、交互式提问卡片(阿布需要你拍板时直接在对话里出选项,单选 / 多选)、计划模式(高风险任务先出计划、等你批准再执行)、模型能力徽章 + Token 用量统计(基于 models.dev 维护的模型能力表)。
每个版本的完整 changelog 见 Releases。
简洁直观的界面,强大灵活的能力
SOUL.md 自定义语气、称呼、回复风格、边界让阿布成为你的团队机器人 — 在 IM 中 @阿布 即可对话:
~/.abu/memory/ 多文件目录,跨项目生效,自动按主题分文件存储,MEMORY.md 作为索引注入对话~/.abu/projects/<工作区>/memory/ 自动按工作区隔离,每条记忆为独立 .md 文件,便于阅读、搜索和回收~/.abu/agents/abu/memory.md 和 {workspace}/.abu/MEMORY.md 启动时自动迁移到新结构~/.abu/ABU.md — 用户级规则(跨项目){workspace}/.abu/ABU.md — 项目级规则{workspace}/.abu/rules/*.md — 模块化规则(按字母序加载,最多 20 个文件)sandbox-exec) / Windows PowerShell ConstrainedLanguage,隔离 shell 命令的文件访问范围rm -rf / 等)静态识别详细功能说明请查看 使用指南
前往 GitHub Releases 下载最新版本:
| 平台 | 文件 |
|---|---|
| macOS (Apple Silicon) | Abu_x.x.x_aarch64.dmg |
| macOS (Intel) | Abu_x.x.x_x64.dmg |
| Windows | Abu_x.x.x_x64-setup.exe |
macOS 用户注意:首次打开如提示"已损坏",需执行
xattr -cr /Applications/Abu.app,详见 安装指南。
打开 Abu → 设置 → AI 服务管理:
回到主界面,用模型选择器选择你想用的模型,然后开始对话。
试试这些指令:
帮我整理下桌面的文件,按类型分类放好
把这个 PDF 里的表格提取出来,生成 Excel
每天早上 9 点帮我搜索最新的 AI 新闻,生成日报
用前端技能帮我做一个产品 landing page
帮我做一份本周的工作周报 PPT