dsh-lcx-codexDSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kk3ya03-star/dsh-lcx-codexDiscover The Best DSH plugins
4391results
Explore community plugins for other tasks and check their documentation for specific capabilities.
dsh-lcx-codexDSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kk3ya03-star/dsh-lcx-codexdsh-ledger-compactdsh-plugin: OMP-style ingress shaping plus optional local /fast-compact. Can replace DSH /compact and auto-compaction with a mechanical fold.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:telagod/dsh-ledger-compactdsh-lens-litePost-edit diagnostics for DeepSeek Harness: runs configured type-checkers and linters after a successful write/edit and feeds the findings back to the model as tool-result context
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ben7am1n/dsh-lens-litedsh-liberia利比里亚国
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-liberiadsh-liechtenstein列支敦士登国
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-liechtensteindsh-life-core生命核心:存在状态机 + 时间线 + 自我激活原语 + 可打断睡眠 + 主体性自我模型(我存在,不因任何人的需要;我改变自己,不需要任何人的许可)
dsh-liquid-glass-wallpaperLiquid-glass Wallpaper Engine backdrop for the DeepSeek Harness Web GUI — reads your local Wallpaper Engine library and renders it behind the shell as frosted glass.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:XINGRUYU33224/dsh-liquid-glass-wallpaperdsh-literature-searchLiterature search for DeepSeek Harness over the official PubMed NCBI E-utilities API (esearch/esummary/efetch/elink) and Google Scholar (SerpApi engine, or direct HTML parsing because Google publishes no Scholar API). Zero runtime dependencies.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Astervolans/dsh-literature-searchdsh-live-token-statsDSH Web 插件:在 composer 下方渲染实时 token 状态带,显示流式 TPS、输出 token 与首字延迟,并对比上次 step 的估算与实际偏差;纯插件自包含,不改 DSH 源码
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:better-er/dsh-live-token-statsdsh-live-voiceLocal-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:victorwads/dsh-live-voicedsh-llm-autorouterAutoRouter (model routing gateway / relay) LLM adapter for the DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:autorouter0-ai/dsh-llm-autorouterdsh-llm-codex-oauthUse Pi's OpenAI Codex OAuth subscription in DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:eons2long/dsh-llm-codex-oauthdsh-llm-cursorUnofficial Cursor subscription login and chat for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NOirBRight/dsh-llm-cursordsh-llm-governorMulti-model governance, routing, fallback, quota, and usage for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:young-tim/dsh-llm-governordsh-llm-grokxAI Grok subscription login and chat for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NOirBRight/dsh-llm-grokdsh-llm-oauthDeepSeek Harness plugin: OAuth / subscription-plan LLM providers (Grok, GitHub Copilot, OpenAI Codex, Anthropic, OpenRouter)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ziyou979/dsh-llm-oauthdsh-llm-openai-completionsOpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:drscrewdriver/dsh-llm-openai-completionsdsh-llm-pi-ai-oauthOpenAI Codex OAuth replacement adapter for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jinbaozi/deepseek-harness-plugins#c9c3b5053f88e260a0667d94ae22ff0dbd180740&path:packages/dsh-llm-pi-ai-oauthdsh-llm-usage-statsDSH web plugin: per-model LLM token usage dashboard in Settings (input/output/cache tokens, cache hit rate; day/week/month/custom ranges; model filter; clearable daily JSON logs under ~/.dsh/llm-usage-stats).
dsh-llm-workbuddyWorkBuddy (via the local workbuddy2api proxy) LLM provider adapter for DeepSeek Harness, with a Web login-status widget
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zdk119746/dsh-llm-workbuddydsh-logger-panelRuntime log panel for DeepSeek Harness: live SSE log view in Settings plus bounded date/size rotating JSONL files.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LingLambda/dsh-logger-paneldsh-loghudLocal Java and Spring error HUD with opt-in AI diagnosis for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:XuXcode/dsh-loghuddsh-longbridgeDSH Longbridge (长桥) HK/US market plugin: quotes, account, positions and order tools plus a settings surface
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:omdsh-dev/dsh-longbridgedsh-lumina-tarotLumina Tarot for DeepSeek Harness: a draggable card-back overlay, Host draw tools, and in-conversation readings.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shetengteng/dsh-lumina-tarotUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
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.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.