Discover The Best DSH plugins

DeepSeek Harness plugins — Page 351

22016results

Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.

dsh-openwiki

openwiki 知识库:DSH 内嵌代码库 Wiki 生成与阅读(复用 DSH 模型、运行时托管、生成/更新任务、知识卡片)。

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:D2Moqi/dsh-openwiki
dsh-operating-context

DeepSeek Harness settings page: cap every configured model service to a working context window, clamped to what each model can actually hold

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AIMFllyYS/dsh-operating-context
dsh-opg-usage

OpenCode Go 套餐额度实时查看面板:可拖拽、可收缩的浮动胶囊,显示滚动/本周/本月窗口的已用与剩余额度。

Financial data · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:M4sh1r0-444/dsh-opg-usage
dsh-orca-glass

真·液态玻璃折射层(Liquid glass refraction)for the orca-scene DSH web skin: injects an SVG feTurbulence+feDisplacementMap filter and applies it through backdrop-filter, plus grain, pointer specular, caustics animation, floating glass cards and scrollbar polish.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:huzhengbang2007/dsh-orca-glass
dsh-os-agent-plugin

Self-contained Volcengine Mobile Use Agent runtime and configuration UI for DeepSeek Harness.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chenjie1129/deepseek-harness-os-agent-plugin
dsh-otel

OpenTelemetry plugin for DeepSeek Harness (dsh) — traces and metrics for agent runs, tools, and model calls

Agent collaboration
dsh-outcome-loop

Local-first task outcome ledger & acceptance plugin for DeepSeek Harness (DSH): evidence-backed verification of task completion, zero extra model cost, user-owned sidecar data. 任务结果账本与验收插件:机械证据验收、默认零额外 token、数据本地持有。

Financial data
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:victorzhong0110/dsh-outcome-loop
dsh-outline

DSH web plugin: search and read an Outline knowledge base from conversations, with approved, whitelist-guarded document writes.

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:huangfuren/dsh-outline
dsh-output-setting

DSH output settings: auto-expand reasoning/tool nodes, code block font size and line height, and model output language (auto / Chinese / English)

Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yijiezhong/dsh-output-setting
dsh-ov-memory

OpenViking memory & context bundle for DeepSeek Harness: auto-recall, session capture, threshold commit, offline outbox replay, self-contained MCP tool bridge, viking:// URI guard.

Memory and knowledge · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaono1/dsh-ov-memory

dsh-p2m

★ 1
dsh-p2m

DSH 冲突管家(P2M):自动拦截会让 DSH 闪退的同名服务注册/版本漂移等冲突,按用时排序、隔离肇事插件。Plugin Conflict Manager for DeepSeek Harness (DSH/Cordis).

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:GiantAxeint/DSH-P2M
dsh-pace-popups

One-install bundle for 知识疆域 (Knowledge Territory): mounts the atlas map, its feeders (crosslens card draw, jiyibi notes), the floating bar, the shared skin, and the optional grasp-probe nudge together. Add this one package to get them all; switch any off in the bar. A dsh bundle (dsh.bundle.patch → cordis.patch.yml).

Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiayuhkust/knowledge-territory#a82d6e2cd53291d90592ae07f57dfe87b6ecdab9&path:packages/suite
dsh-paddle-ocr

DSH PaddleOCR (百度 PaddleOCR-VL 文档布局解析) plugin: OCR tools plus a settings card and task panel

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:omdsh-dev/dsh-paddle-ocr
dsh-pain-point-check

Enforced pain-point-check guard plugin for DeepSeek Harness: after two non-converged experiments on one problem it injects the three questions, denies non-investigative tool calls until they are answered in the reply text, and blocks same-direction retries

Agent collaboration
dsh-palenight-theme

Persistent DeepSeek Palenight Theme for dsh — a dsh client bundle (survives restarts, unlike the dynamic-plugin form).

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:youyli03/dsh-palenight-theme
dsh-paper-gogo-plugin

Expose the Paper-gogo evidence-first paper workflow (18 Phase, G0-G6 gates, four-state evidence audit) as DeepSeek Harness tools.

Skills · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gqallen931/paper-gogo-plugin
dsh-paperlens

文献检索科研副驾驶插件 for DeepSeek Harness — multi-source academic search, citation formatting (APA/MLA/GB-T-7714/Chicago/Vancouver), RIS/BibTeX/CSV export, and a local sqlite library. Inspired by the PaperLens workflow (find/screen/read/understand/store/cite), fully source-level rewritten as a native Cordis plugin.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:masquerator-coder/dsh-paperlens
dsh-password-gate

Password login gateway plugin for dsh web: first-open password setup, login, and password change with real request interception.

Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xbzbing/dsh-password-gate
dsh-password-prompt

DeepSeek Harness plugin: a masked password input panel in the Web GUI. The agent calls the password_prompt tool, the browser pops an HTML password panel, and the typed value is returned to the agent — no interactive terminal needed.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MagicCrazyMan/dsh-password-prompt
dsh-paste-preview

DeepSeek Harness (dsh) web plugin: paste images into the composer with thumbnail previews, route them as file attachments for text-only models, and show zoomable thumbnails in sent messages

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wertyq111/dsh-paste-preview
dsh-patch-apply

dsh-patch-apply — apply structured unified diffs (git format) to the real filesystem inside DeepSeek Harness: multi-file/multi-hunk parsing, fuzzy hunk location with line-offset correction, all-or-nothing application with precise conflict reports, automatic reverse-patch undo, dry-run, and undo journaling. Zero runtime dependencies.

Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JohnXu22786/apply-patch
dsh-patchouli

Native knowledge context for DeepSeek Harness

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:memorax-ai/dsh-patchouli
dsh-patrol

Browser patrol and website inspection plugin for DeepSeek Harness: teach once, replay deterministic runbooks with managed Chromium, credentials, screenshots, checkpoints, and selector recovery.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qigelunbiya/DSH-Patrol
dsh-pc-pilot

PC-Pilot - lightweight Windows + Chromium computer-use runtime, CLI, and DeepSeek Harness host plugin.

Vision tools · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JeremyWangCY/dsh-pc-pilot

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.