Living Dream DSH 🚀

Living Dream DSH — The Ultimate DeepSeek Harness Desktop Configuration

A battle-tested DSH configuration framework with 8+ MCP servers, custom plugins, free model access, mobile remote control, and more.

📖 English | 简体中文

🆚 Living Dream DSH vs. Mainstream AI Coding Frameworks

Data as of 2026-08. Prices from official pages. Living-Dream-DSH is an open-source DSH config pack (MIT).

Overview

Dimension	Living-Dream-DSH (this repo)	Claude Code	GitHub Copilot	Cursor	OpenHands	Aider	Cline
Positioning	DSH open-source config pack: GUI installer + 8+ MCP + plugins + free model channels	Anthropic official CLI/desktop agent	GitHub official IDE assistant	Commercial AI IDE	Open-source web agent (OpenDevin successor)	Open-source git-native CLI agent	Open-source VS Code agent plugin
Price	$0 (built-in free channels, or BYOK)	Free / Pro $20/mo / Max 5x $100 / Max 20x $200	Pro $10/mo+, Business $19/seat	Pro $20/mo, Ultra $200/mo	Free (BYOK, enterprise extra)	Free (BYOK)	Free (BYOK, enterprise extra)
Model flexibility	✅ Multi-channel BYOK: DeepSeek, AMD Radeon (free), OpenCode Go, Zhipu Vision	❌ Claude only	⚠️ GitHub ecosystem bound	⚠️ Multiple models	✅ Any OpenAI-compatible	✅ Any model	✅ Any model
MCP servers (out-of-box)	✅ 8+ ready to use: desktop/browser/OCR/memory/doc conversion/code exec/vision/history	⚠️ Native MCP, self-configure each	⚠️ Limited MCP	⚠️ MCP, self-configure	⚠️ MCP, self-configure	⚠️ MCP, self-configure	⚠️ MCP, self-configure
Desktop automation (screenshot/click/keyboard)	✅ computer-use MCP	⚠️ computer use (Beta)	❌	❌	❌	❌	❌
Browser control	✅ Playwright MCP (real login state)	⚠️ computer use (Beta)	❌	❌	⚠️ Experimental	❌	⚠️ Browser Use (experimental)
Screen OCR	✅ Offline Windows OCR	❌	❌	❌	❌	❌	❌
Doc conversion (PDF/Word/Excel → Markdown)	✅ MarkItDown MCP	❌	❌	❌	❌	❌	❌
Long-term memory	✅ Semantic search (local vector store)	✅ CLAUDE.md / memory files	⚠️ Limited	⚠️ Rules level	⚠️ Session-level	❌ Git history only	⚠️ Project rules
File drag & paste upload	✅ Custom plugin (drag + Ctrl+V + first-time guide)	⚠️ Partial	✅ IDE native	✅ IDE native	⚠️ Web upload	❌	⚠️ Paste
Mobile remote access	✅ Tailscale + proxy rewrite	✅ Official app / web	❌	❌	✅ Web UI	❌	❌
Chinese ecosystem	✅ Full Chinese docs + troubleshooting + anti-pitfall guide	❌ English only	❌	❌	❌	❌	❌
Open source / License	✅ MIT (incl. custom plugins)	❌ Closed	❌ Closed	❌ Closed	✅ MIT	✅ Apache-2.0	✅ Apache-2.0
Data privacy / self-host	✅ Local-first, your keys	❌ Anthropic cloud	❌ Microsoft cloud	❌ Cloud	✅ Self-hostable	✅ Fully local	✅ Fully local
Install effort	✅ GUI installer (env detect/config/shortcut auto)	✅ Easy	✅ Easy	✅ Easy	⚠️ Docker/env needed	✅ Easy	✅ Easy
Free quota	✅ AMD Radeon free + DeepSeek signup bonus + Zhipu free vision	⚠️ Free tier limited	⚠️ Trial quota	⚠️ Trial quota	❌ BYOK only	❌ BYOK only	❌ BYOK only

Why Choose Living-Dream-DSH?

Zero cost: The only "out-of-box and fully free" option. Claude Code costs $100–200/mo for heavy use; Copilot/Cursor start at $10–20/mo. This repo integrates multiple free model channels (AMD Radeon Cloud, DeepSeek signup bonus, Zhipu GLM-4V-Flash free vision), lowering the barrier to $0 while keeping BYOK for upgrades.
Full-stack capability: 8+ MCP servers out of the box — desktop automation, browser control, screen OCR, doc conversion, semantic memory, code execution. Others either don't support these or require manual per-server setup. One install = full toolkit, every component battle-tested (pitfalls documented in the troubleshooting guide).
Chinese ecosystem: The only full-Chinese one-stop solution. Complete Chinese docs, troubleshooting manual, and anti-pitfall guide. Commercial products and OSS projects are predominantly English, which is a real barrier for Chinese users.
Open source + self-built: MIT license — configs, scripts, custom plugin source all public. Local-first, API keys stay with you. No vendor lock-in vs. closed-source Claude Code/Copilot/Cursor; vs. OSS trio (OpenHands/Aider/Cline), adds the "pre-integrated config" layer.
Mobile office: Tailscale-based remote access from phone browser — a capability most CLI/IDE competitors (Aider, Cline, Cursor) lack.

Caveats

Free channels depend on third-party policies; stability and quotas are subject to change. Heavy/commercial use recommended with BYOK or commercial subscriptions.
This repo is a DSH config pack, not an independent agent kernel; the "framework ceiling" depends on official DSH capabilities.
Comparison based on public info; some features (Claude Code computer use, Cline Browser Use) are still in Beta.

Quick Decision Guide

Your situation	Recommendation
Zero-cost full-stack agent (code + desktop + browser + remote)	Living-Dream-DSH
Willing to pay for best model quality, OK with English	Claude Code
Heavy VS Code / GitHub workflow	GitHub Copilot
Want a graphical AI IDE	Cursor
Prefer pure OSS, DIY environment	OpenHands / Aider / Cline

✨ Features

Feature	Description
🔌 8+ MCP Servers	History/Vision/Desktop/Code Execution/Browser/Memory/Document/OCR
🤖 Free Model Access	AMD Radeon Cloud + DeepSeek Signup Bonus + Zhipu Free Vision
📱 Mobile Remote Access	Tailscale + Proxy, control DSH from phone
🖼️ Auto Image Recognition	GLM-4V-Flash free vision (Desktop only)
📁 File Drag & Drop	Custom dsh-file-uploads plugin
🔐 Secure Key Storage	DPAPI-encrypted backup (`secrets.json` + `secrets.ps1`) alongside plaintext `.credentials.yaml`
🛡️ Troubleshooting Guide	All pitfalls and solutions documented

📁 Directory Structure

Living-Dream-DSH/
├── README.md                    # English
├── README.zh.md                 # Chinese
├── LICENSE                      # MIT License
├── .gitignore
├── setup.ps1                    # Headless setup script (run by installer)
├── installer-v2.iss             # Inno Setup script (online installer)
├── installer-v2-offline.iss     # Inno Setup script (offline installer)
├── install-gui.ps1              # GUI installer (MPC-HC style wizard)
├── install-gui-offline.ps1      # Offline GUI installer (uses bundled deps)
├── install.ps1                  # CLI installer (fallback)
├── install.bat                  # Installer launcher
├── package.json                 # repo scripts deps (http-proxy for proxy.js)
├── configs/
│   ├── cordis.patch.yml.template   # MCP config template
│   ├── package.json.template       # Plugin list template
│   ├── settings.yaml.template      # Global settings template
│   ├── AGENTS.md                   # AI instructions
│   ├── .credentials.yaml.template  # API Key template
│   └── README.md                   # Config file guide
├── scripts/
│   ├── start-dsh.bat.template      # DSH launcher
│   ├── create-dsh-shortcut.ps1     # Desktop shortcut helper (post-install)
│   ├── proxy.js                    # Phone remote proxy (CORS rewrite)
│   ├── secrets.ps1                 # DPAPI key decryption (reads secrets.json)
│   ├── os-copilot-mcp-server.py    # OS-Copilot MCP (legacy location)
│   ├── os-copilot-mcp-README.md    # OS-Copilot MCP docs
│   ├── os-copilot-mcp-LICENSE      # OS-Copilot MIT license
│   └── mcp/                        # MCP server scripts (all 6 bundled)
│       ├── dsh-history-server.py
│       ├── dsh-vision-server.py
│       ├── dsh-memory-server.py
│       ├── store_engine.py         # Memory engine (SQLite + vector search)
│       ├── dsh-markitdown-server.py
│       ├── dsh-ocr-server.py
│       └── os-copilot-server.py
├── plugins/
│   ├── README.md                   # Plugin installation guide
│   └── dsh-paste-input/            # Custom file drag & paste plugin
│       ├── package.json
│       ├── lib/
│       │   ├── index.js
│       │   └── client.js
│       ├── cordis.patch.yml
│       ├── README.md
│       └── LICENSE
└── docs/
    ├── comparison.md               # EN comparison table (7 frameworks)
    ├── comparison.zh.md            # ZH comparison table
    ├── phone-remote.md             # Mobile remote access tutorial
    ├── vision-patch.md             # Image recognition patch
    └── troubleshooting.md          # Troubleshooting manual

🚀 Quick Start

Prerequisites (Must Install First)

Software	Version	Download	Required
DeepSeek Harness Desktop	v1.1.0+	GitHub Releases	✅ Yes
Node.js	v22+ (Recommended v24 LTS)	nodejs.org	✅ Yes
Python	3.13+	python.org	✅ Yes
pnpm	Latest	`npm install -g pnpm`	✅ Yes
Git	Any	git-scm.com	For clone

💡 After installing Python, run pip install mcp markitdown zstandard to enable all MCP servers. The GUI installer does this automatically.

💡 The launcher auto-detects DSH Desktop from common install paths. If it fails, set $env:DSH_DESKTOP_PATH = "D:\Tools\DeepSeekHarness-Desktop" (your actual path), or add it as a system environment variable for persistence.

Option 1: Offline Install ⭐ Recommended

No internet required during install. Node.js, Python, Git are bundled in the package.

Download Living-Dream-DSH-v2.7.9-Offline-Setup.exe (~122 MB) from Releases
Double-click to run — professional Inno Setup wizard launches
Follow the wizard: Language → License → Choose Install Location → Install
After extraction, the headless setup script runs automatically (in a visible PowerShell window):
- Installs Node.js, Python, Git from bundled files (no download)
- Copies configs to ~/.dsh
- Installs plugin dependencies
- Creates desktop shortcut
- Finish page: optional "Add DeepSeek Harness to desktop" checkbox
- After install: fill in API Keys in DSH Settings

💡 There is also an online installer Living-Dream-DSH-v2.7.9-Setup.exe (~2 MB) that downloads dependencies via winget.

Option 2: GUI Installer (Source Build)

# 1. Clone repository
git clone https://github.com/alllllllllli/Living-Dream-DSH.git
cd Living-Dream-DSH

# 2. Double-click install.bat (launches GUI wizard)
#    Or run in PowerShell: .\install-gui.ps1

The GUI installer walks you through:

✅ Welcome → License Agreement → Choose Install Location
✅ Auto-check environment (Node.js, Python, pnpm, Git)
✅ Copy config files to ~/.dsh
✅ Install plugin dependencies
✅ Create desktop shortcut
✅ After install: fill in API Keys in DSH Settings

Option 3: Manual Install

Click to expand manual installation steps

Step-by-Step

# 1. Install prerequisites (if not installed)
winget install OpenJS.NodeJS.LTS        # Node.js
winget install Python.Python.3.13       # Python
npm install -g pnpm                      # pnpm

# 2. Clone repository
git clone https://github.com/alllllllllli/Living-Dream-DSH.git
cd Living-Dream-DSH

# 3. Copy config files to DSH directory
Copy-Item configs\cordis.patch.yml.template $env:USERPROFILE\.dsh\profiles\web\cordis.patch.yml
Copy-Item configs\package.json.template $env:USERPROFILE\.dsh\profiles\web\package.json
Copy-Item configs\settings.yaml.template $env:USERPROFILE\.dsh\settings.yaml
Copy-Item configs\AGENTS.md $env:USERPROFILE\.dsh\AGENTS.md
Copy-Item configs\.credentials.yaml.template $env:USERPROFILE\.dsh\.credentials.yaml

# 4. Edit config files (fill in your API Keys)
notepad $env:USERPROFILE\.dsh\.credentials.yaml

# 5. Install plugins (dsh-paste-input is a file: dependency - bundled in repo)
Copy-Item plugins\dsh-paste-input $env:USERPROFILE\.dsh\profiles\plugins\dsh-paste-input -Recurse
cd $env:USERPROFILE\.dsh\profiles\web
pnpm install

# 6. Restart DSH Desktop

🔌 MCP Server List

All server scripts are bundled in scripts/mcp/. GUI installer configures paths automatically.

MCP	Function	Script	Extra Dependencies
`dsh-history`	Session history search	`scripts/mcp/dsh-history-server.py`	`pip install mcp zstandard`
`dsh-vision`	Image analysis (Ollama)	`scripts/mcp/dsh-vision-server.py`	Ollama + qwen2.5vl model
`dsh-computer`	Desktop automation	— (npx)	`@zavora-ai/computer-use-mcp` (auto-installed)
`os-copilot`	Code execution	`scripts/mcp/os-copilot-server.py`	`pip install mcp`
`dsh-browser`	Browser automation	— (npx)	`@playwright/mcp` (auto-installed)
`dsh-memory`	Long-term memory	`scripts/mcp/dsh-memory-server.py`	Bundled store_engine + Ollama bge-m3
`dsh-markitdown`	Document → Markdown	`scripts/mcp/dsh-markitdown-server.py`	`pip install mcp markitdown`
`dsh-ocr`	Screen OCR (Windows)	`scripts/mcp/dsh-ocr-server.py`	`pip install mcp`, Windows 10+

🤖 Free Model Access

AMD Radeon Cloud

Endpoint: https://developer.amd.com.cn/radeon/api/v1
Model: DeepSeek-V4-Flash
Register: developer.amd.com.cn/radeon

📱 Mobile Remote Access

Access DSH from phone browser via Tailscale:

# 1. Install Tailscale
winget install tailscale.tailscale

# 2. Login to same account
tailscale up

# 3. Start the rewrite proxy (must go through 8090 - DSH Web UI has CORS
#    checks, connecting directly to 3080 fails)
npm install http-proxy                  # one-time dependency
node scripts/proxy.js                   # listens on 127.0.0.1:8090

# 4. Configure serve (point to the 8090 proxy, NOT 3080)
tailscale serve --https=443 --bg http://127.0.0.1:8090

# 5. Access from phone browser
# https://<your-device-name>.<your-domain>.ts.net

See docs/phone-remote.md

🖼️ Image Recognition Patch

Make DSH Desktop auto-call GLM-4V-Flash for image recognition:

# 1. Backup original file
$dshPath = (Get-Process DeepSeekHarness* -ErrorAction SilentlyContinue).Path
if (-not $dshPath) { $dshPath = "D:\Tools\DeepSeek-Harness-Desktop" }
Copy-Item "$dshPath\resources\runtime\node_modules\@deepseek-ai\dsh-host-apiproxy\lib\index.js" `
          "$env:USERPROFILE\dsh-host-apiproxy-index.js.bak"

# 2. Apply patch (manually modify describeImagesLocally function around line 911)
# See docs/vision-patch.md

⚠️ Note: DSH upgrades will overwrite this patch, re-apply after upgrade.

🛡️ Troubleshooting

1. Plugin Installation

# ✅ Correct way
dsh plugin --profile web add <package>@<version>

# ❌ Wrong way (will clear unlisted bundles)
cd $env:USERPROFILE\.dsh\profiles\web
pnpm add <package>

2. Desktop vs Dev Version Conflict

Both share ~/.dsh, causing concurrent write conflicts. Close Dev version (port 3080) when using Desktop.

3. Image Patch

DSH upgrades will overwrite dsh-host-apiproxy modifications, re-apply patch.

4. billion-context-dsh Version

Must lock version 0.2.1, default will misparse as 0.1.7 (no dsh.bundle).

📝 Configuration Files

cordis.patch.yml

MCP server config file at ~/.dsh/profiles/web/cordis.patch.yml

# Example: Add an MCP server
- insert:
    - id: mcp-dsh-example
      name: '@deepseek-ai/dsh-mcp-client'
      config:
        transport: stdio
        serverName: dsh-example
        command: python
        args:
          - path/to/server.py
        env: {}
        cwd: ''
        toolCallTimeoutMs: 120000
        failOnStartupError: false

settings.yaml

Global settings file at ~/.dsh/settings.yaml

# Configure model providers
llm-pi-ai:
  providers:
    my-provider:
      apiKeyEnv: MY_API_KEY
      api: openai-completions
      baseURL: https://api.example.com/v1
      models:
        - id: my-model
          name: My Model
          contextWindow: 1000000

.credentials.yaml

API Key storage at ~/.dsh/.credentials.yaml

MY_API_KEY: sk-xxxxxxxxxxxx

🔧 Custom Extensions

Add New MCP Server

Create MCP server (reference existing implementations)
Add config to cordis.patch.yml
Add plugin to package.json bundles (if needed)
Restart DSH Desktop

Create Custom Plugin

Reference dsh-file-uploads plugin structure.

📚 Resources

🤝 Contributing

Issues and Pull Requests are welcome!

📄 License

This project is licensed under the MIT License.

👤 Author


GitHub	@alllllllllli
Bilibili	UID 608277472
QQ	2896722915

🙏 Acknowledgments

Living Dream DSH stands on the shoulders of these amazing open-source projects and services:

Core Platform

Project	What we use it for
DeepSeek Harness	The entire DSH framework this project configures
Model Context Protocol (MCP)	Protocol standard by Anthropic that powers all our server integrations
FastMCP	Python framework we use to build all custom MCP servers

MCP Servers & Engines

Project	What we use it for
Playwright MCP	Browser automation with real login state
computer-use-mcp	Desktop automation (screenshot/click/keyboard), MIT licensed
MarkItDown	Document conversion (PDF/Word/Excel → Markdown)
memory-mcp	`store_engine.py` — SQLite + vector search memory engine
OS-Copilot	Desktop automation framework (OSWorld benchmark winner)
Windows OCR	Built-in offline screen text recognition

AI Models & Services

Project	What we use it for
Zhipu AI (GLM-4V-Flash)	Free vision model for image understanding
Ollama	Local model inference (vision fallback + embedding)
AMD Radeon Cloud	Free DeepSeek model access (v4-flash / v4-pro)

DSH Plugins

Plugin	Author / Source
billion-context-dsh	Long context support (must pin v0.2.1)
dsh-rss	RSS feed reader
dsh-calendar	Calendar management (CalDAV)
dsh-email	Email client
dsh-ffmpeg	Video/audio processing
@xiaweiliang060035/dsh-opencode-go-usage	OpenCode Go usage widget
@anionex/dsh-vision-toolkit	Vision tools for DSH
dsh-file-uploads	Upstream of our bundled `dsh-paste-input` plugin

Infrastructure & Tools

Project	What we use it for
Tailscale	WireGuard mesh VPN for mobile remote access
http-proxy	Node.js CORS proxy for phone → DSH bridge
Inno Setup	Professional Windows installer (replaces 7z SFX)

Last Updated: 2026-08-18 (Inno Setup installer)

Living Dream DSH 🚀

Living Dream DSH — The Ultimate DeepSeek Harness Desktop Configuration

A battle-tested DSH configuration framework with 8+ MCP servers, custom plugins, free model access, mobile remote control, and more.

📖 English | 简体中文

🆚 Living Dream DSH vs. Mainstream AI Coding Frameworks

Data as of 2026-08. Prices from official pages. Living-Dream-DSH is an open-source DSH config pack (MIT).

Overview

Dimension	Living-Dream-DSH (this repo)	Claude Code	GitHub Copilot	Cursor	OpenHands	Aider	Cline
Positioning	DSH open-source config pack: GUI installer + 8+ MCP + plugins + free model channels	Anthropic official CLI/desktop agent	GitHub official IDE assistant	Commercial AI IDE	Open-source web agent (OpenDevin successor)	Open-source git-native CLI agent	Open-source VS Code agent plugin
Price	$0 (built-in free channels, or BYOK)	Free / Pro $20/mo / Max 5x $100 / Max 20x $200	Pro $10/mo+, Business $19/seat	Pro $20/mo, Ultra $200/mo	Free (BYOK, enterprise extra)	Free (BYOK)	Free (BYOK, enterprise extra)
Model flexibility	✅ Multi-channel BYOK: DeepSeek, AMD Radeon (free), OpenCode Go, Zhipu Vision	❌ Claude only	⚠️ GitHub ecosystem bound	⚠️ Multiple models	✅ Any OpenAI-compatible	✅ Any model	✅ Any model
MCP servers (out-of-box)	✅ 8+ ready to use: desktop/browser/OCR/memory/doc conversion/code exec/vision/history	⚠️ Native MCP, self-configure each	⚠️ Limited MCP	⚠️ MCP, self-configure	⚠️ MCP, self-configure	⚠️ MCP, self-configure	⚠️ MCP, self-configure
Desktop automation (screenshot/click/keyboard)	✅ computer-use MCP	⚠️ computer use (Beta)	❌	❌	❌	❌	❌
Browser control	✅ Playwright MCP (real login state)	⚠️ computer use (Beta)	❌	❌	⚠️ Experimental	❌	⚠️ Browser Use (experimental)
Screen OCR	✅ Offline Windows OCR	❌	❌	❌	❌	❌	❌
Doc conversion (PDF/Word/Excel → Markdown)	✅ MarkItDown MCP	❌	❌	❌	❌	❌	❌
Long-term memory	✅ Semantic search (local vector store)	✅ CLAUDE.md / memory files	⚠️ Limited	⚠️ Rules level	⚠️ Session-level	❌ Git history only	⚠️ Project rules
File drag & paste upload	✅ Custom plugin (drag + Ctrl+V + first-time guide)	⚠️ Partial	✅ IDE native	✅ IDE native	⚠️ Web upload	❌	⚠️ Paste
Mobile remote access	✅ Tailscale + proxy rewrite	✅ Official app / web	❌	❌	✅ Web UI	❌	❌
Chinese ecosystem	✅ Full Chinese docs + troubleshooting + anti-pitfall guide	❌ English only	❌	❌	❌	❌	❌
Open source / License	✅ MIT (incl. custom plugins)	❌ Closed	❌ Closed	❌ Closed	✅ MIT	✅ Apache-2.0	✅ Apache-2.0
Data privacy / self-host	✅ Local-first, your keys	❌ Anthropic cloud	❌ Microsoft cloud	❌ Cloud	✅ Self-hostable	✅ Fully local	✅ Fully local
Install effort	✅ GUI installer (env detect/config/shortcut auto)	✅ Easy	✅ Easy	✅ Easy	⚠️ Docker/env needed	✅ Easy	✅ Easy
Free quota	✅ AMD Radeon free + DeepSeek signup bonus + Zhipu free vision	⚠️ Free tier limited	⚠️ Trial quota	⚠️ Trial quota	❌ BYOK only	❌ BYOK only	❌ BYOK only

Why Choose Living-Dream-DSH?

Zero cost: The only "out-of-box and fully free" option. Claude Code costs $100–200/mo for heavy use; Copilot/Cursor start at $10–20/mo. This repo integrates multiple free model channels (AMD Radeon Cloud, DeepSeek signup bonus, Zhipu GLM-4V-Flash free vision), lowering the barrier to $0 while keeping BYOK for upgrades.
Full-stack capability: 8+ MCP servers out of the box — desktop automation, browser control, screen OCR, doc conversion, semantic memory, code execution. Others either don't support these or require manual per-server setup. One install = full toolkit, every component battle-tested (pitfalls documented in the troubleshooting guide).
Chinese ecosystem: The only full-Chinese one-stop solution. Complete Chinese docs, troubleshooting manual, and anti-pitfall guide. Commercial products and OSS projects are predominantly English, which is a real barrier for Chinese users.
Open source + self-built: MIT license — configs, scripts, custom plugin source all public. Local-first, API keys stay with you. No vendor lock-in vs. closed-source Claude Code/Copilot/Cursor; vs. OSS trio (OpenHands/Aider/Cline), adds the "pre-integrated config" layer.
Mobile office: Tailscale-based remote access from phone browser — a capability most CLI/IDE competitors (Aider, Cline, Cursor) lack.

Caveats

Free channels depend on third-party policies; stability and quotas are subject to change. Heavy/commercial use recommended with BYOK or commercial subscriptions.
This repo is a DSH config pack, not an independent agent kernel; the "framework ceiling" depends on official DSH capabilities.
Comparison based on public info; some features (Claude Code computer use, Cline Browser Use) are still in Beta.

Quick Decision Guide

Your situation	Recommendation
Zero-cost full-stack agent (code + desktop + browser + remote)	Living-Dream-DSH
Willing to pay for best model quality, OK with English	Claude Code
Heavy VS Code / GitHub workflow	GitHub Copilot
Want a graphical AI IDE	Cursor
Prefer pure OSS, DIY environment	OpenHands / Aider / Cline

✨ Features

Feature	Description
🔌 8+ MCP Servers	History/Vision/Desktop/Code Execution/Browser/Memory/Document/OCR
🤖 Free Model Access	AMD Radeon Cloud + DeepSeek Signup Bonus + Zhipu Free Vision
📱 Mobile Remote Access	Tailscale + Proxy, control DSH from phone
🖼️ Auto Image Recognition	GLM-4V-Flash free vision (Desktop only)
📁 File Drag & Drop	Custom dsh-file-uploads plugin
🔐 Secure Key Storage	DPAPI-encrypted backup (`secrets.json` + `secrets.ps1`) alongside plaintext `.credentials.yaml`
🛡️ Troubleshooting Guide	All pitfalls and solutions documented

📁 Directory Structure

Living-Dream-DSH/
├── README.md                    # English
├── README.zh.md                 # Chinese
├── LICENSE                      # MIT License
├── .gitignore
├── setup.ps1                    # Headless setup script (run by installer)
├── installer-v2.iss             # Inno Setup script (online installer)
├── installer-v2-offline.iss     # Inno Setup script (offline installer)
├── install-gui.ps1              # GUI installer (MPC-HC style wizard)
├── install-gui-offline.ps1      # Offline GUI installer (uses bundled deps)
├── install.ps1                  # CLI installer (fallback)
├── install.bat                  # Installer launcher
├── package.json                 # repo scripts deps (http-proxy for proxy.js)
├── configs/
│   ├── cordis.patch.yml.template   # MCP config template
│   ├── package.json.template       # Plugin list template
│   ├── settings.yaml.template      # Global settings template
│   ├── AGENTS.md                   # AI instructions
│   ├── .credentials.yaml.template  # API Key template
│   └── README.md                   # Config file guide
├── scripts/
│   ├── start-dsh.bat.template      # DSH launcher
│   ├── create-dsh-shortcut.ps1     # Desktop shortcut helper (post-install)
│   ├── proxy.js                    # Phone remote proxy (CORS rewrite)
│   ├── secrets.ps1                 # DPAPI key decryption (reads secrets.json)
│   ├── os-copilot-mcp-server.py    # OS-Copilot MCP (legacy location)
│   ├── os-copilot-mcp-README.md    # OS-Copilot MCP docs
│   ├── os-copilot-mcp-LICENSE      # OS-Copilot MIT license
│   └── mcp/                        # MCP server scripts (all 6 bundled)
│       ├── dsh-history-server.py
│       ├── dsh-vision-server.py
│       ├── dsh-memory-server.py
│       ├── store_engine.py         # Memory engine (SQLite + vector search)
│       ├── dsh-markitdown-server.py
│       ├── dsh-ocr-server.py
│       └── os-copilot-server.py
├── plugins/
│   ├── README.md                   # Plugin installation guide
│   └── dsh-paste-input/            # Custom file drag & paste plugin
│       ├── package.json
│       ├── lib/
│       │   ├── index.js
│       │   └── client.js
│       ├── cordis.patch.yml
│       ├── README.md
│       └── LICENSE
└── docs/
    ├── comparison.md               # EN comparison table (7 frameworks)
    ├── comparison.zh.md            # ZH comparison table
    ├── phone-remote.md             # Mobile remote access tutorial
    ├── vision-patch.md             # Image recognition patch
    └── troubleshooting.md          # Troubleshooting manual

🚀 Quick Start

Prerequisites (Must Install First)

Software	Version	Download	Required
DeepSeek Harness Desktop	v1.1.0+	GitHub Releases	✅ Yes
Node.js	v22+ (Recommended v24 LTS)	nodejs.org	✅ Yes
Python	3.13+	python.org	✅ Yes
pnpm	Latest	`npm install -g pnpm`	✅ Yes
Git	Any	git-scm.com	For clone

💡 After installing Python, run pip install mcp markitdown zstandard to enable all MCP servers. The GUI installer does this automatically.

💡 The launcher auto-detects DSH Desktop from common install paths. If it fails, set $env:DSH_DESKTOP_PATH = "D:\Tools\DeepSeekHarness-Desktop" (your actual path), or add it as a system environment variable for persistence.

Option 1: Offline Install ⭐ Recommended

No internet required during install. Node.js, Python, Git are bundled in the package.

Download Living-Dream-DSH-v2.7.9-Offline-Setup.exe (~122 MB) from Releases
Double-click to run — professional Inno Setup wizard launches
Follow the wizard: Language → License → Choose Install Location → Install
After extraction, the headless setup script runs automatically (in a visible PowerShell window):
- Installs Node.js, Python, Git from bundled files (no download)
- Copies configs to ~/.dsh
- Installs plugin dependencies
- Creates desktop shortcut
- Finish page: optional "Add DeepSeek Harness to desktop" checkbox
- After install: fill in API Keys in DSH Settings

💡 There is also an online installer Living-Dream-DSH-v2.7.9-Setup.exe (~2 MB) that downloads dependencies via winget.

Option 2: GUI Installer (Source Build)

# 1. Clone repository
git clone https://github.com/alllllllllli/Living-Dream-DSH.git
cd Living-Dream-DSH

# 2. Double-click install.bat (launches GUI wizard)
#    Or run in PowerShell: .\install-gui.ps1

The GUI installer walks you through:

✅ Welcome → License Agreement → Choose Install Location
✅ Auto-check environment (Node.js, Python, pnpm, Git)
✅ Copy config files to ~/.dsh
✅ Install plugin dependencies
✅ Create desktop shortcut
✅ After install: fill in API Keys in DSH Settings

Option 3: Manual Install

Click to expand manual installation steps

Step-by-Step

# 1. Install prerequisites (if not installed)
winget install OpenJS.NodeJS.LTS        # Node.js
winget install Python.Python.3.13       # Python
npm install -g pnpm                      # pnpm

# 2. Clone repository
git clone https://github.com/alllllllllli/Living-Dream-DSH.git
cd Living-Dream-DSH

# 3. Copy config files to DSH directory
Copy-Item configs\cordis.patch.yml.template $env:USERPROFILE\.dsh\profiles\web\cordis.patch.yml
Copy-Item configs\package.json.template $env:USERPROFILE\.dsh\profiles\web\package.json
Copy-Item configs\settings.yaml.template $env:USERPROFILE\.dsh\settings.yaml
Copy-Item configs\AGENTS.md $env:USERPROFILE\.dsh\AGENTS.md
Copy-Item configs\.credentials.yaml.template $env:USERPROFILE\.dsh\.credentials.yaml

# 4. Edit config files (fill in your API Keys)
notepad $env:USERPROFILE\.dsh\.credentials.yaml

# 5. Install plugins (dsh-paste-input is a file: dependency - bundled in repo)
Copy-Item plugins\dsh-paste-input $env:USERPROFILE\.dsh\profiles\plugins\dsh-paste-input -Recurse
cd $env:USERPROFILE\.dsh\profiles\web
pnpm install

# 6. Restart DSH Desktop

🔌 MCP Server List

All server scripts are bundled in scripts/mcp/. GUI installer configures paths automatically.

MCP	Function	Script	Extra Dependencies
`dsh-history`	Session history search	`scripts/mcp/dsh-history-server.py`	`pip install mcp zstandard`
`dsh-vision`	Image analysis (Ollama)	`scripts/mcp/dsh-vision-server.py`	Ollama + qwen2.5vl model
`dsh-computer`	Desktop automation	— (npx)	`@zavora-ai/computer-use-mcp` (auto-installed)
`os-copilot`	Code execution	`scripts/mcp/os-copilot-server.py`	`pip install mcp`
`dsh-browser`	Browser automation	— (npx)	`@playwright/mcp` (auto-installed)
`dsh-memory`	Long-term memory	`scripts/mcp/dsh-memory-server.py`	Bundled store_engine + Ollama bge-m3
`dsh-markitdown`	Document → Markdown	`scripts/mcp/dsh-markitdown-server.py`	`pip install mcp markitdown`
`dsh-ocr`	Screen OCR (Windows)	`scripts/mcp/dsh-ocr-server.py`	`pip install mcp`, Windows 10+

🤖 Free Model Access

AMD Radeon Cloud

Endpoint: https://developer.amd.com.cn/radeon/api/v1
Model: DeepSeek-V4-Flash
Register: developer.amd.com.cn/radeon

📱 Mobile Remote Access

Access DSH from phone browser via Tailscale:

# 1. Install Tailscale
winget install tailscale.tailscale

# 2. Login to same account
tailscale up

# 3. Start the rewrite proxy (must go through 8090 - DSH Web UI has CORS
#    checks, connecting directly to 3080 fails)
npm install http-proxy                  # one-time dependency
node scripts/proxy.js                   # listens on 127.0.0.1:8090

# 4. Configure serve (point to the 8090 proxy, NOT 3080)
tailscale serve --https=443 --bg http://127.0.0.1:8090

# 5. Access from phone browser
# https://<your-device-name>.<your-domain>.ts.net

See docs/phone-remote.md

🖼️ Image Recognition Patch

Make DSH Desktop auto-call GLM-4V-Flash for image recognition:

# 1. Backup original file
$dshPath = (Get-Process DeepSeekHarness* -ErrorAction SilentlyContinue).Path
if (-not $dshPath) { $dshPath = "D:\Tools\DeepSeek-Harness-Desktop" }
Copy-Item "$dshPath\resources\runtime\node_modules\@deepseek-ai\dsh-host-apiproxy\lib\index.js" `
          "$env:USERPROFILE\dsh-host-apiproxy-index.js.bak"

# 2. Apply patch (manually modify describeImagesLocally function around line 911)
# See docs/vision-patch.md

⚠️ Note: DSH upgrades will overwrite this patch, re-apply after upgrade.

🛡️ Troubleshooting

1. Plugin Installation

# ✅ Correct way
dsh plugin --profile web add <package>@<version>

# ❌ Wrong way (will clear unlisted bundles)
cd $env:USERPROFILE\.dsh\profiles\web
pnpm add <package>

2. Desktop vs Dev Version Conflict

Both share ~/.dsh, causing concurrent write conflicts. Close Dev version (port 3080) when using Desktop.

3. Image Patch

DSH upgrades will overwrite dsh-host-apiproxy modifications, re-apply patch.

4. billion-context-dsh Version

Must lock version 0.2.1, default will misparse as 0.1.7 (no dsh.bundle).

📝 Configuration Files

cordis.patch.yml

MCP server config file at ~/.dsh/profiles/web/cordis.patch.yml

# Example: Add an MCP server
- insert:
    - id: mcp-dsh-example
      name: '@deepseek-ai/dsh-mcp-client'
      config:
        transport: stdio
        serverName: dsh-example
        command: python
        args:
          - path/to/server.py
        env: {}
        cwd: ''
        toolCallTimeoutMs: 120000
        failOnStartupError: false

settings.yaml

Global settings file at ~/.dsh/settings.yaml

# Configure model providers
llm-pi-ai:
  providers:
    my-provider:
      apiKeyEnv: MY_API_KEY
      api: openai-completions
      baseURL: https://api.example.com/v1
      models:
        - id: my-model
          name: My Model
          contextWindow: 1000000

.credentials.yaml

API Key storage at ~/.dsh/.credentials.yaml

MY_API_KEY: sk-xxxxxxxxxxxx

🔧 Custom Extensions

Add New MCP Server

Create MCP server (reference existing implementations)
Add config to cordis.patch.yml
Add plugin to package.json bundles (if needed)
Restart DSH Desktop

Create Custom Plugin

Reference dsh-file-uploads plugin structure.

📚 Resources

🤝 Contributing

Issues and Pull Requests are welcome!

📄 License

This project is licensed under the MIT License.

👤 Author


GitHub	@alllllllllli
Bilibili	UID 608277472
QQ	2896722915

🙏 Acknowledgments

Living Dream DSH stands on the shoulders of these amazing open-source projects and services:

Core Platform

Project	What we use it for
DeepSeek Harness	The entire DSH framework this project configures
Model Context Protocol (MCP)	Protocol standard by Anthropic that powers all our server integrations
FastMCP	Python framework we use to build all custom MCP servers

MCP Servers & Engines

Project	What we use it for
Playwright MCP	Browser automation with real login state
computer-use-mcp	Desktop automation (screenshot/click/keyboard), MIT licensed
MarkItDown	Document conversion (PDF/Word/Excel → Markdown)
memory-mcp	`store_engine.py` — SQLite + vector search memory engine
OS-Copilot	Desktop automation framework (OSWorld benchmark winner)
Windows OCR	Built-in offline screen text recognition

AI Models & Services

Project	What we use it for
Zhipu AI (GLM-4V-Flash)	Free vision model for image understanding
Ollama	Local model inference (vision fallback + embedding)
AMD Radeon Cloud	Free DeepSeek model access (v4-flash / v4-pro)

DSH Plugins

Plugin	Author / Source
billion-context-dsh	Long context support (must pin v0.2.1)
dsh-rss	RSS feed reader
dsh-calendar	Calendar management (CalDAV)
dsh-email	Email client
dsh-ffmpeg	Video/audio processing
@xiaweiliang060035/dsh-opencode-go-usage	OpenCode Go usage widget
@anionex/dsh-vision-toolkit	Vision tools for DSH
dsh-file-uploads	Upstream of our bundled `dsh-paste-input` plugin

Infrastructure & Tools

Project	What we use it for
Tailscale	WireGuard mesh VPN for mobile remote access
http-proxy	Node.js CORS proxy for phone → DSH bridge
Inno Setup	Professional Windows installer (replaces 7z SFX)

Last Updated: 2026-08-18 (Inno Setup installer)

Living-Dream-DSH

Living Dream DSH 🚀

🆚 Living Dream DSH vs. Mainstream AI Coding Frameworks

Overview

Why Choose Living-Dream-DSH?

Caveats

Quick Decision Guide

✨ Features

📁 Directory Structure

🚀 Quick Start

Prerequisites (Must Install First)

Option 1: Offline Install ⭐ Recommended

Option 2: GUI Installer (Source Build)

Option 3: Manual Install

Step-by-Step

🔌 MCP Server List

🤖 Free Model Access

AMD Radeon Cloud

📱 Mobile Remote Access

🖼️ Image Recognition Patch

🛡️ Troubleshooting

1. Plugin Installation

2. Desktop vs Dev Version Conflict

3. Image Patch

4. billion-context-dsh Version

📝 Configuration Files

cordis.patch.yml

settings.yaml

.credentials.yaml

🔧 Custom Extensions

Add New MCP Server

Create Custom Plugin

📚 Resources

🤝 Contributing

📄 License

👤 Author

🙏 Acknowledgments

Core Platform

MCP Servers & Engines

AI Models & Services

DSH Plugins

Infrastructure & Tools

社区评论

Living-Dream-DSH

Living Dream DSH 🚀

🆚 Living Dream DSH vs. Mainstream AI Coding Frameworks

Overview

Why Choose Living-Dream-DSH?

Caveats

Quick Decision Guide

✨ Features

📁 Directory Structure

🚀 Quick Start

Prerequisites (Must Install First)

Option 1: Offline Install ⭐ Recommended

Option 2: GUI Installer (Source Build)

Option 3: Manual Install

Step-by-Step

🔌 MCP Server List

🤖 Free Model Access

AMD Radeon Cloud

📱 Mobile Remote Access

🖼️ Image Recognition Patch

🛡️ Troubleshooting

1. Plugin Installation

2. Desktop vs Dev Version Conflict

3. Image Patch

4. billion-context-dsh Version

📝 Configuration Files

cordis.patch.yml

settings.yaml

.credentials.yaml

🔧 Custom Extensions

Add New MCP Server

Create Custom Plugin

📚 Resources

🤝 Contributing

📄 License

👤 Author

🙏 Acknowledgments