You're Invited:Meet the Socket Team at RSAC and BSidesSF 2026, March 23–26.RSVP
Socket
Book a DemoSign in
Socket

deepseek-cowork

Package Overview
Dependencies
Maintainers
1
Versions
35
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

deepseek-cowork

Open-Source Alternative to Claude Cowork - CLI Tool

latest
Source
npmnpm
Version
0.1.35
Version published
Weekly downloads
26
-66.67%
Maintainers
1
Weekly downloads
 
Created
Source

DeepSeek Cowork

DeepSeek Cowork banner

License: MIT Version Electron Node.js

English | 中文文档

DEMO

https://github.com/user-attachments/assets/a744dd83-0689-4fbe-8638-be0fe5e32935

Why This Project?

On January 13, 2026, Anthropic released Claude Cowork:

"Introducing Cowork: Claude Code for the rest of your work."

Great product, but:

Claude CoworkDeepSeek Cowork
Price💰 Expensive✅ Ultra-low cost
Accessibility🔒 Complex setup, regional restrictions✅ Ready to use
Open Source❌ Proprietary✅ Fully open source
Self-hosting❌ Not supported✅ Supports private deployment

We want everyone to have access to a great AI assistant — so we built this.

Why DeepSeek?

Solid BaselineUltra AffordableFully Open
Reliable performance among open-source LLMsMost competitive API pricingSupports local deployment & customization

Core Philosophy

Open-source models will eventually catch up with closed-source.

We believe it's only a matter of time. Rather than wait, we're building the infrastructure now.

When open-source models reach parity, DeepSeek Cowork will be ready.

Why Now?

This would have been impossible before. But two things changed:

  • AI Coding explosion - Dramatically reduced development costs, enabling individuals to build complex applications
  • Engineering bridges the gap - Prompt engineering, skill systems, and context management can enhance the experience on existing models

What Can It Do?

Use natural language to have AI help you with:

  • 🌐 Browser Automation - Open pages, batch fill forms, extract data, cross-site operations
  • 📁 File Management - Browse, organize, and preview your workspace files
  • 🧠 Persistent Memory - AI remembers conversation context, understands your habits

Typical Scenarios

ScenarioExample
Data Collection"Extract prices from these 10 pages and make a spreadsheet"
Form Filling"Batch fill registration forms using this contact list"
Content Organization"Sort files in my downloads folder by type"
Monitoring"Check this page daily and notify me of updates"

💡 Like having a 24/7 digital assistant at your command

Technical Documentation

Architecture Highlights

DeepSeek Cowork adopts a unique Hybrid SaaS architecture, combining the best of cloud-based SaaS and local desktop applications:

┌─────────────────────────────────────────────────────────────────┐
│                        User's Computer                          │
│  ┌──────────────┐    ┌──────────────┐    ┌──────────────────┐  │
│  │   Electron   │    │  Web Browser │    │   CLI Tool       │  │
│  │   Desktop    │    │  (Chrome,    │    │ deepseek-cowork  │  │
│  │     App      │    │   Edge...)   │    │                  │  │
│  └──────┬───────┘    └──────┬───────┘    └────────┬─────────┘  │
│         │ IPC               │ HTTP/WS             │ manage     │
│         └───────────────────┼─────────────────────┘            │
│                             ▼                                   │
│                    ┌────────────────┐                          │
│                    │  LocalService  │◄── All data stays local  │
│                    │  (Node.js)     │                          │
│                    └────────┬───────┘                          │
└─────────────────────────────┼───────────────────────────────────┘
                              │ Encrypted
                              ▼
                    ┌────────────────┐
                    │   Happy AI     │
                    │   (Cloud)      │
                    └────────────────┘
FeatureBenefit
Zero Server CostStatic frontend hosted on GitHub Pages, no backend infrastructure needed
Data PrivacyAll user data, settings, and files remain on your local machine
Unified ExperienceSame UI/UX whether using Desktop app or Web browser

How It Works

  • Desktop Mode: Electron app communicates with LocalService via IPC
  • Web Mode: Browser connects to LocalService via HTTP/WebSocket on localhost:3333
  • CLI Mode: Manage LocalService directly from terminal

The ApiAdapter layer automatically detects the environment and routes API calls appropriately.

Happy Integration

DeepSeek Cowork integrates with Happy, an open-source mobile and web client for AI coding agents.

FeatureDescription
End-to-End EncryptionAll messages are encrypted locally before transmission - your data never leaves your device unencrypted
Mobile AccessUse the Happy App (iOS / Android) to monitor and control AI tasks on the go
Push NotificationsGet alerted when AI needs permission or encounters errors
Open SourceFully auditable code with no telemetry or tracking

DeepSeek Cowork uses Happy's account server for session management and encrypted sync across devices.

Core Components

ComponentDescription
Claude CodeOriginal Claude Code integrated as Agent kernel with all features and capabilities
HappyOpen-source AI session management with E2E encryption and mobile app support
JS EyesBrowser extension for tab control, script execution, data extraction
Electron AppCross-platform desktop interface integrating all components

Quick Start

git clone https://github.com/imjszhang/deepseek-cowork.git
cd deepseek-cowork
npm install
npm start

Development mode: npm run dev

Web Version (Hybrid SaaS)

Use DeepSeek Cowork directly in your browser without installing the desktop app.

Online Demo

Visit deepseek-cowork.com to try the web interface.

Prerequisites

  • Node.js 18+
  • npm or yarn

Setup Local Service

# Install CLI tool globally (latest version: 0.1.35)
npm install -g deepseek-cowork@0.1.35

# Start local service (background mode)
deepseek-cowork start --daemon

# Open web interface in browser
deepseek-cowork open

CLI Commands Reference

CLI Version: deepseek-cowork@0.1.35

CommandDescription
deepseek-cowork startStart local service (foreground)
deepseek-cowork start --daemonStart local service (background)
deepseek-cowork stopStop local service
deepseek-cowork statusCheck service status
deepseek-cowork openOpen web interface in browser
deepseek-cowork configView/edit configuration
deepseek-cowork deployDeploy skills to work directories
deepseek-cowork moduleManage server modules

Deploy Skills

# Deploy built-in skills to work directories
deepseek-cowork deploy

# Deploy with Chinese templates
deepseek-cowork deploy --lang zh

# Deploy custom skill from any path
deepseek-cowork deploy --from ./my-skill --target my-project

# Check deployment status
deepseek-cowork deploy status

Manage Server Modules

# List available modules
deepseek-cowork module list

# Deploy a module
deepseek-cowork module deploy demo-module

# Deploy custom module from any path
deepseek-cowork module deploy my-module --from ./my-module-source

# Check deployed modules status
deepseek-cowork module status

Build Web Version

# Build static files for web deployment
npm run build:web

# Output: docs/app/

The web frontend is deployed to GitHub Pages automatically.

Building Desktop Clients

Build standalone installers for Windows, macOS, and Linux:

# Build for current platform
npm run build

# Build for specific platform
npm run build:win    # Windows (NSIS installer + portable)
npm run build:mac    # macOS (DMG, Intel + Apple Silicon)
npm run build:linux  # Linux (AppImage, deb, rpm)

# Build for all platforms
npm run build:all

Built packages will be output to the dist/ directory.

Version Management

The project uses semantic versioning (SemVer). Current version: V0.1.35

Update version numbers:

npm run version:patch   # 0.1.0 → 0.1.1 (bug fixes)
npm run version:minor   # 0.1.0 → 0.2.0 (new features)
npm run version:major   # 0.1.0 → 1.0.0 (breaking changes)

The version number is automatically synchronized to:

  • package.json - Source of truth
  • renderer/index.html - UI display (auto-updated during build)
  • Application runtime - Dynamically loaded from package.json

Browser Extension

Browser automation requires the JS Eyes extension.

Installation

  • Download JS Eyes
  • Open browser extension page
    • Chrome: chrome://extensions/
    • Edge: edge://extensions/
    • Firefox: about:debugging
  • Enable "Developer mode"
  • Click "Load unpacked" and select the extension folder for your browser
  • Make sure DeepSeek Cowork is running, extension will auto-connect

See JS Eyes documentation for details

Contributing

PRs welcome! Fork → Change → Submit.

License

MIT

Acknowledgments

This project is built upon:

  • Happy - AI session management client
  • JS Eyes - Browser automation extension
  • Electron - Cross-platform desktop framework
  • DeepSeek - Open-source LLM

Making great AI assistants accessible to everyone

X

Keywords

deepseek

FAQs

Package last updated on 11 Feb 2026

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts