Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
Pinned sessions for DeepSeek Harness: a 「置顶」 group in the sidebar — native-shaped session rows for every pinned session across workspaces, right above the Workspace browser, with an in-place search.
Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:439436269-ctrl/dsh-pinned-sessions
VibeDev 插件中心:集中了解、一键安装和管理 VibeDev 官方插件,支持套装、旧包名迁移,并可一键安装社区插件市场 · VibeDev Plugin Center: learn about, one-click install and manage the official VibeDev plugins, with suites, legacy-package migration, and a one-click install of the community plugin market
Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:VibeDev-Si/dsh-ecosystem
右侧栏媒体预览:直接预览视频、音频和 HTML(大文件可拖进度条,HTML 默认允许脚本),并提供文件夹媒体画廊,需配合 dsh-better-sidebar · Inline video, audio and HTML preview plus a folder media gallery in the dsh-better-sidebar right column — range-streamed large files, sandboxed HTML with working relative assets
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:VibeDev-Si/dsh-media-viewer
VibeDev 账号与模型:在 DeepSeek Harness 里登录 VibeDev,与 DeepSeek 账号并存,使用 VibeDev 网关的模型(Claude、GPT 等),并生成图片、视频、音乐和播客 · VibeDev account and models for DeepSeek Harness: sign in to VibeDev next to the DeepSeek account and use the VibeDev gateway's models (Claude, GPT and more), plus image, video, music and podcast generation
Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:VibeDev-Si/dsh-vibedev
Per-session agent loop engine router for DSH — run Claude Code, Codex, pi, or the in-process loop per session, all on DSH's unified session, LLM, and tracing substrate
Long-form novel assistant for DeepSeek Harness: a story ledger (characters/assets/relations/emotions), chapter anchors with reconciliation, foreshadow debt audit, and 14 narrative invariants checked by hard rules — zero mis-kills. Every claim carries an experiment number.
Knowledge-base and memory switch for dsh web: a three-position memory button in the composer tool row (left of the model selector) plus 「我的知识库」 and 「Cherry Studio 知识库」 settings pages. The host half orchestrates the local 我的知识库 toolchain (记忆开关 / idx / cherry) and re-implements neither indexing nor memory. Requires that toolchain; point DSH_KB_ROOT at it.
Memory and knowledge
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wanghuiym123/dsh-cherry-kb
Draggable quota/cost dashboard for the dsh web GUI: combines OpenRouter and DeepSeek balances and spend (official APIs + local ledger) in one movable card.
Financial data · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wangyong1972/dsh-quota-dashboard
Audit DeepSeek Harness disk usage (sessions, attachments, rebuildable caches), classify it by risk, and move anything you choose to delete into the plugin's own recoverable trash. The model can query, never delete.
Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:was35/dsh-reclaim
Surgical rewriting of the model-visible conversation history of a DSH session (surface replacement); edit reply and reasoning chain separately. 上下文手术刀:强制改写会话的模型可见历史,回复与思考链分开编辑。
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
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.