Discover The Best DSH plugins

Vision tools · DeepSeek Harness plugins — Page 23

2403results

Find image understanding, screenshot analysis and visual interaction plugins; compare inputs and usage.

@chaiyahang/dsh-scratchpad

Scratchpad panel for DeepSeek Harness: tagged notes, image and file attachments, Markdown preview with clickable tasks, send-to-chat with real attachments, a wake-up shortcut, JSON export/import, and Agent tools over Host-side storage.

Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Chaiyahang/dsh-scratchpad
@chance722/dsh-inbox

Personal paste inbox for DeepSeek Harness (dsh): capture, classify, browse and retrieve.

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Chance722/dsh-inbox
@chang416/deepsee

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

Skills · Agent collaboration · Vision tools · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chang416/deepsee
@crosery/dsh-drop

Drag and paste files into dsh Web with a unified preview rail; keep native images and add file references only when sending.

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Crosery/dsh-drop
@cxzrdxy/dsh-file-explorer

DeepSeek Harness plugin: an in-workspace file tree, a peer view tab that previews text and image files (single-click auto-switches to the tab, double-click opens straight in edit mode), drag-to-composer file paths, create/delete file and folder operations with DSH-native dialogs and smooth DSH-token animations.

Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cxzrdxy/dsh-file-explorer
@ddtcorex/maestro-reviewer

Maestro Reviewer: the AI merge request review engine and its GitLab CI flow (resolve job, reviewer image, templates)

Vision tools · Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add @ddtcorex/maestro-reviewer
@deepseek-ai/dsh-acp

Automation-only Agent Client Protocol server for driving DeepSeek Harness agents over JSON-RPC stdio

Skills · Agent collaboration · Vision tools · Productivity
@deepseek-ai/dsh-api-remotes

Remote BFF assembly and Host Agent/Session lookup policy

Skills · Agent collaboration · Vision tools · Integrations · Productivity
@deepseek-ai/dsh-app-boot

Shared boot glue for the app bins: .env loading, fail-loud Loader guards, snapshot-aware config resolution, and the Loader boot sequence

Skills · Agent collaboration · Vision tools
@deepseek-ai/dsh-base

The shared dsh core as a profile bundle: every profile's first patch layer, inserting the base plugin rows over the empty profile root

Skills · Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SuperMate-Ai/SuperMate-Harness-System#f842280c993ba87672d4a926cd26c2e979740440&path:plugins/DSH Official/packages/bundle/base
@deepseek-ai/dsh-browser-use

Browser-use capability seam (ctx.browserUse): isolated per-Agent Playwright Chromium contexts with DNS-pinned guarded navigation, semantic and screenshot-bound coordinate actions

Agent collaboration · Vision tools
@deepseek-ai/dsh-client-connection

Wire consumer layer: HTTP-up/WebSocket-down client, ConnectionController dual streams with reconnect, and fixture api

Skills · Agent collaboration · Vision tools
@deepseek-ai/dsh-client-hmr

Dev-only hot-reload driver for script-loaded client entries: SSE rebuilt frames → invalidate/prefetch → fiber swap through the vendored Loader entry

Skills · Agent collaboration · Vision tools
@deepseek-ai/dsh-client-locale

Locale plugin: Host-backed zh/en preference, browser-derived fallback, locale snapshots, and typed namespace dictionaries

Skills · Agent collaboration · Vision tools
@deepseek-ai/dsh-client-modules

Client module system, dual-face: node half composes the __DSH_BOOT__ entry graph (incremental dsh.client scan, bundle route, index tap, webPlugins service); browser half is the lazy-CJS module table the vendored cordis Loader consumes as its internal seam

Skills · Agent collaboration · Vision tools
@deepseek-ai/dsh-client-schema-form

Schema/draft model layer for settings editors: rehydrates a serialized schemastery schema, validates drafts, and edits them immutably by path

Skills · Agent collaboration · Vision tools
@deepseek-ai/dsh-client-ui-agent-preset

Agent-preset surfaces: the default for later sessions, this session's seat, and the composition editor

Skills · Agent collaboration · Vision tools · Interface extensions · Productivity
@deepseek-ai/dsh-client-ui-attachment

Pure React attachment atoms for the dsh web UI: draft-image rail, message image gallery, and original-image lightbox (zero cordis)

Agent collaboration · Vision tools · Interface extensions
@deepseek-ai/dsh-client-ui-attachment

Pure React attachment atoms for the dsh web UI: draft-image rail, message image gallery, and original-image lightbox (zero cordis)

Vision tools · Interface extensions · Productivity
@deepseek-ai/dsh-client-ui-attachment

Dynamic attachment presentation plugin for conversation input, message-image, and trajectory image slots

Vision tools · Interface extensions · Developer tools

Find the right plugin, then get started

  1. Search by task

    Use a feature keyword or category, then sort by recent updates or GitHub stars.

  2. Explore capabilities

    Read the description, AI analysis and original README to understand what a plugin does.

  3. Check and install

    Review compatibility, dependency ranges and instructions, then copy the available install command.

Questions about DSH Hub

What is DSH Hub?

DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.

Does inclusion mean a plugin is tested and compatible?

No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.

How do I install a plugin?

Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.