DeepSeek Harness Plugin
🔍 中文

deepseek-harness-desktop-app

💬 Sessions & Messages ⭐ 112 stars DSH Plugin

A local AI desktop workspace built on DeepSeek Harness, bringing sessions, projects, files, web research, plugins, and Office artifacts together in one app for daily work.

Plugin facts

GitHub stars⭐ 112
LicenseMIT
Primary languageJavaScript
Last push2026-08-15T08:56:28Z
Maintainervibeinging
Added to this directory2026-08-15

Screenshots

deepseek-harness-desktop-app screenshot 1
deepseek-harness-desktop-app screenshot 2

About this plugin

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

Install this DSH plugin

Copy the command below and run it in your DeepSeek Harness terminal.

dsh plugin add github:vibeinging/deepseek-harness-desktop-app

⚠️ Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →

About this plugin: deepseek-harness-desktop-app

What is deepseek-harness-desktop-app?

deepseek-harness-desktop-app is a sessions & messages plugin maintained by vibeinging. A local AI desktop workspace built on DeepSeek Harness, bringing sessions, projects, files, web research, plugins, and Office artifacts together in one app for daily work.

How do I install deepseek-harness-desktop-app?

Run dsh plugin add github:vibeinging/deepseek-harness-desktop-app in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:vibeinging/deepseek-harness-desktop-app#commit.

Is deepseek-harness-desktop-app free?

deepseek-harness-desktop-app is a community open-source project released under the MIT license. You can inspect its source and install it for free.

Sessions & Messages

A task-aware reasoning-mode router for DeepSeek Harness. Each task is placed on one continuous react-to-spec axis, the router picks from three measured behavior bands before the first model request, and persona plus first-turn tool injection are supported with agent-visible tuning.

View plugin → yjh051108