HomeTutorials

Install DSH on Windows

Download the official Windows x64 installer, connect a model and verify your first task.

Maintained by DeepSeekDSH (independent site)Updated: 2026-10-21

On this page

Download DSH Desktop for Windows

Download Windows x64 installer Use the PowerShell / CLI path →

The official EXE includes its runtime; no separate Node.js installation is needed. Have a Windows x64 computer, internet access and your model-provider credentials ready. Model API credits are separate.

Install and openStart with the downloaded EXE
Connect a modelSave credentials and select a model
Verify a first taskCheck the test folder and actual result

STEP 1

Download and install DSH Desktop for Windows

Find dsh-latest-windows-x64.exe in your browser's downloads. Check that it came from download.deepseek.com and finished downloading.
Open the EXE and follow the installer's prompts.
Open DeepSeek Harness from the Windows Start menu. Continue with model setup below.

Back up Desktop data before updating

A Windows user reported missing workspace records, sessions and plugin state after updating from 0.2.1-rc.5 to 0.2.2-rc.1, while project files remained. The cause and an official fix have not been confirmed. Before updating, quit DSH, identify the actual DSH_HOME path and back it up separately. The backup can contain credentials; keep it secure. Read the user report ↗

Download not starting? Open the full Desktop download page →

Success check

You can find and open DSH Desktop.

STEP 2

Open DSH Desktop

Open DeepSeek Harness Desktop. Follow its first-run prompts, then add your own model provider credentials.

Success check

The DSH main window opens normally.

STEP 3

Configure a model provider

If you use the official DeepSeek API, create a key at DeepSeek API Keys. In DSH, open Settings → Models → DeepSeek, paste the key and save it.

DeepSeek Harness model settings showing the DeepSeek provider — Official model settings screenshot from source snapshot c291e79; labels may differ by release.

Success check

The model picker lets you select a model from the configured provider.

STEP 4

Choose an empty test folder

Create a folder named dsh-test, then choose it with Choose workspace. Do not start with a production repository or a folder that contains secrets.

Success check

The selected workspace is C:\dsh-test or the equivalent dsh-test folder you created.

STEP 5

Verify the setup with one read-only task

Send this prompt:

Use tools to report the full path of the current workspace and list the files in it. Do not create, edit or delete any files.

The setup is working when

① the model replies; ② the reported workspace is your dsh-test folder; ③ the file list matches what is on disk; ④ no error is shown.

If something fails, find the matching symptom

The desktop app will not openCheck the installer and Desktop FAQ The composer is disabledCheck the selected model and workspace

node or npm is not recognized

Close Terminal and reopen it. If the command still fails, repair the Node.js installation or PATH. Desktop users do not need Node.js for the packaged app.

npm reports an unsupported Node engine

Run node --version. Requirements vary by DSH version. v0.2.2-alpha.2 requires >=24.9.0; check your installed package before changing Node.

npx looks stuck on first launch

The first run may be downloading the package. If npm asks to install @deepseek-ai/dsh, confirm the package name before accepting. Do not start several copies while the first one is still starting.

EADDRINUSE on port 3080

Run Get-NetTCPConnection -LocalPort 3080 -State Listen. Stop the stale process or start DSH on another port, for example npx @deepseek-ai/dsh web --port 13080.

EACCES on port 3080 with no listener

Hyper-V, WSL2 or Docker Desktop can reserve TCP ranges. Run netsh interface ipv4 show excludedportrange protocol=tcp. If 3080 is reserved, use a port outside the excluded range.

MISSING_CREDENTIAL

Open Settings → Models and save the provider credential again.

UNKNOWN_MODEL

Open Settings → Models and choose a model that the configured provider currently exposes.

Provider or model errorCheck the API key, selected provider and live model picker Another errorStart from the exact error message or visible symptom

Command-line setup (advanced)

Use this path only if you specifically want the CLI or local Web UI outside DSH Desktop.

Install Node.js from the official Node.js downloads page, then use the recommended range below.

Install Node.js in the recommended range >=24.9.0.
Press the Windows key, search for Terminal, open Windows Terminal and use PowerShell.
Run node --version and npm --version.
Run npx @deepseek-ai/dsh web.
Open http://127.0.0.1:3080, then continue from Step 3 above.

node --version
npm --version

npx @deepseek-ai/dsh web

Keep the terminal open and use its full printed URL. Open the startup command reference →

Optional: use DSH from a chat platform

Do this only after the local setup works. Pick one platform you already use; you do not need to configure all of them.

Quick personal test

Use a Telegram bot as a remote entry point for DSH tasks.

Connection: Create a bot with BotFather → add the token

Open setup guide Server and channel workflows

Discord

Use DSH from an existing Discord server or channel.

Connection: Create a Discord bot → add the token and permissions

Open setup guide WeChat-first workflow

WeChat

Connect the community dsh-im route through an iLink QR code.

Connection: Scan the iLink QR code

Open setup guide WhatsApp self-chat

Start with a linked-device flow and test in your own chat.

Connection: Link a WhatsApp Web device

Open setup guide Team chat

Feishu / Lark

Use DSH in direct messages or team channels.

Connection: Scan to create, or add App ID / App Secret

Open setup guide

Sources and compatibility

Official Desktop documentation, Desktop downloads. The historical source snapshot declares ^22.19.0 || >=24.0.0; v0.2.2-alpha.2 requires >=24.9.0. Check your DSH version.