dsh-miniprogram-helperDSH 插件:扫描、生成、注册、校验微信小程序页面与配置,并联动微信开发者工具出预览二维码
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:leo666-cloud/dsh-miniprogram-helperDiscover The Best DSH plugins
25610results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-miniprogram-helperDSH 插件:扫描、生成、注册、校验微信小程序页面与配置,并联动微信开发者工具出预览二维码
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:leo666-cloud/dsh-miniprogram-helperdsh-missher-brainOptional shared local recall arbitration and provider status for official DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/dsh-missher-braindsh-missher-brainOptional shared local recall arbitration and provider status for official DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/Missher-DSH-Braindsh-missher-enhanceOptional enhancement modules for official DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/dsh-missher-enhancedsh-missher-evolutionPrivacy-bounded self-improvement plugin for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/dsh-missher-evolutiondsh-missher-evolutionPrivacy-bounded self-improvement plugin for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/Missher-DSH-Evolutiondsh-missher-memoryProject-scoped reviewed memory for Cordis with a DeepSeek Harness adapter
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/dsh-missher-memorydsh-missher-memoryProject-scoped reviewed memory for Cordis with a DeepSeek Harness adapter
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Missher12/Missher-DSH-Memorydsh-mistblueGlassic Mist 雾蓝主题:极浅雾蓝界面 + 云端动效背景 + 全弹窗毛玻璃质感;设置持久化开关 + /misttheme 命令
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:VlanTech/dsh-glassic-mist-themedsh-mite-removal除螨建议
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-mite-removaldsh-mj-spiderman-pluginMJ 蜘蛛侠彩蛋插件:任意输入框输入 mj 触发透明悬浮窗特效(视频+json WebGL 合成,DSH Client 插件)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:biteainet/dsh-mj-spiderman-plugindsh-mlopsML 管线工作流:数据→训练→评估→部署→监控的 MLOps 工程。受 wshobson/agents(38k★ MIT)启发。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-mlopsdsh-mlx-local在 Apple Silicon 上用 MLX 框架运行本地大模型:模型目录管理、服务启停、OpenAI 兼容 API,并优化 DSH 自定义提供方的本地思考强度选择。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JshGao/dsh-mlx-localdsh-mmroute多模态路由 for DeepSeek Harness:纯文本模型的每一步请求里的每张图片(用户上传 / 工具返回 / MCP 渲染)都先经多模态理解模型转述为文字再作答,图片类报错自动转述重试,两类模型全程交叉协作。Multimodal router for DSH: every image in every step of a text-only model's stream is transcribed to text by a multimodal understander first; image-related failures auto-recover with a transcription retry.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jmxsxwyzjdwl/dsh-mmroutedsh-mmxMiniMax CLI bridge for DeepSeek Harness (dsh): mmx-backed web search fallback and transparent image understanding, with first-run onboarding and a settings card.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:crazyma99/dsh-mmxdsh-mmx-multimodalMiniMax multimodal capability hub for DeepSeek Harness (DSH). One mmx_multimodal tool covers describe/image/video/speech/music/cover/search/quota; optional web_search takeover; built-in client enhancement renders inline players in the Web GUI.
dsh-mnemon-gcMnemon 记忆体 GC 治理插件:把「冲突驱动的正确性纠错」接进 dsh-mnemon(记忆间新事实取代旧事实 → 标记 superseded → 显式确认后才软删除)。自动巡检只报告、绝不删除。基于 dsh-mnemon 的 createRunner 公共 API。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Zn-Dk/dsh-mnemon-gcdsh-mnemos-continuityCross-model continuity for DeepSeek Harness: memory, skills and rules live in local files, so judgement survives session and model changes. Not about storing more memory — about using it well after the model changes.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xthingillu-sketch/dsh-mnemos-continuitydsh-mnemosyneMnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, embedded skill, auto-setup, optional auto-sync/prefetch, and a Settings panel. Data lives under ~/.dsh/mnemosyne.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:rebron1900/dsh-mnemosynedsh-mnemosyne-memoryMnemosyne 永久记忆插件 - 为 DSH 提供长期记忆、向量搜索和 LLM 反思功能
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fjzzwxp/dsh-mnemosyne-memorydsh-mnn-chatMNN Chat 自定义 API 服务接入 DSH:把手机端 MNN Chat(MnnLlmChat)的 OpenAI 兼容 HTTP 服务注册成 DSH 的一个 LLM provider,可在大龙虾里直接对话
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Coshire90-1135/DSH-MnnChat-Providerdsh-moaMixture of Agents (MoA) tool plugin for DeepSeek Harness — run several models in parallel on the same prompt, then have a stronger aggregator model synthesize a final answer. On-demand tool, zero cost when unused.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:morphlinglan/dsh-moadsh-mobileScan a QR code and use DSH from your phone's browser: watch the tasks running on your computer, reply and approve, live. Same Wi-Fi works out of the box; turn on a free Cloudflare tunnel to use it anywhere. One-time QR pairing, per-device access you can revoke.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:OrderG-X/dsh-mobiledsh-mobile-access手机访问服务:Host/Origin 改写反代 + 配对(扫码/输入地址)+ SSE 设备会话 + cloudflared 隧道(DeepSeek Harness Desktop 内置包)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hyperion2144/dsh-desktop-bun#ed531a862971110a7738679d79fdd123bb37ddda&path:plugins/dsh-mobile-accessUse 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.