Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
178 plugins trouvés
Mimir (mimir-skin)
tommyhedgerow/mimir
Publie une leçon dans la conversation DSH : le socle des dépendances, la question et les dessins du Vault, tracés avec la palette du Vault.
computer-user-vision
xie129716/computer-user-vision
Fork Windows de computer-user : 13 outils `computer_*` pour lire l’écran et piloter souris/clavier. Les routes compatibles image reçoivent la capture comme image réelle avec correspondance exacte image-écran, sans OCR externe ; les éléments sont des références UI Automation pour cliquer le rectangle exact. Ctrl+Alt+Esc arrête tous les appels.
dsh-mmroute
jmxsxwyzjdwl/dsh-mmroute
Routage multimodal transparent pour les modèles texte uniquement : chaque image de chaque appel de modèle est entièrement transcrite (OCR verbatim, données, zones d’incertitude, durci contre l’injection) par votre propre compréhenseur multimodal, avec réexamen ciblé via vision_relook et nouvelle tentative automatique en cas d’échec lié aux images. Aucun point de terminaison intégré, aucun identifiant emprunté.
aura-vision
ck-epsilon/aura-vision
OCR de vision gratuit avec reconnaissance adaptative par tuiles pour documents longs et export Markdown/Word/PNG/Excel.
dsh-vision-analysis
harvey-will/dsh-vision-analysis
Plugin de vision DeepSeek Harness : 8 modes d'analyse (décrire, OCR, données de graphique, revue d'interface, détection d'objets, comparaison, génération de code, débogage), toute API de vision compatible OpenAI ou Anthropic, avec un modèle de vision gratuit intégré et un basculement automatique en cas de limite de débit.
dsh-open-file
hyper-dsh-plugins/dsh-open-file
Téléversement de fichiers arbitraires lié à l'espace de travail, lecture, OCR et rendu pour DeepSeek Harness.
dsh-plugins
zjcdkj/dsh-plugins
Plugin out-of-tree DeepSeek Harness : donne des yeux à un modèle de codage textuel en routant les images vers une route Qwen-VL (DashScope) via ctx.llm et en retournant du texte.
dsh-open-file
hyp6666/dsh-open-file
Upload, lecture, OCR et rendu de fichiers arbitraires liés au workspace pour DeepSeek Harness.
dsh-eyes
leeminjing/dsh-eyes
Vision à la demande pour les modèles DeepSeek texte seul : envoyez des images et le modèle appelle un outil view_image adossé à n'importe quel endpoint de vision compatible OpenAI (Qwen/DashScope par défaut).
dsh-tool-vision
gloryxpnv/dsh-tool-vision
Vision structurée local-first pour agents texte seul : les images partent vers un VLM local compatible OpenAI et reviennent en preuves JSON (résumé, OCR littéral, régions de mise en page, entités/relations, couleurs, incertitude explicite), avec repli anti-hallucination et pont facultatif de collage/envoi ; coût cloud nul, les images ne quittent jamais la machine.
dsh-deepseek-tools
zaofan-make/dsh-deepseek-tools
DSH(deepseek-harness)上使用 DeepSeek 全家桶五件套(联网搜索 / 读链接 / OCR / ASR / TTS)!(DSH-Plugin&full suite of application APIs)
dsh-contract-redline
liuhange789/dsh-contract-redline
Contract risk quick-scan for small businesses: paste a procurement / supply, lease or service contract and get a checklist of high-risk clauses, unbalanced obligations and missing key clauses, each with a short excerpt and a plain-language reason. Rule-based and local-only; no OCR, no network, no legal advice — it never says whether to sign or whether the contract is valid.
workfiles-assistant
songshun1021/workfiles-assistant
Voice-first macOS work-documents assistant for DeepSeek Harness. It keeps a local 7-day ledger of the apps you choose, searches documents only inside folders you approve, and opens the file or page you saw recently from what you say. Window titles and HTTPS addresses are separate per-app opt-ins; it does not take screenshots, run OCR, or read the clipboard or the browser-history database.
phone-use-dsh (dsh)
mig-everything/phone-use-dsh
Agent tools for connected HarmonyOS, Android and iPhone devices, with native controls, on-demand screenshots and OCR, and a multi-device sidebar.
dsh-native-tools
brightstonebody/dsh-native-tools
Four native macOS tools in one plugin — drag-to-screenshot with annotation and OCR, clipboard history, select-to-translate, and a menu bar system monitor (network up/down, CPU and memory, each clickable for per-process rankings). All four features share a single AppKit helper process, are toggled independently, and apply setting changes without restarting the plugin or the process.
dsh-desktop-tools
1997liuyh-boop/dsh-desktop-tools
DSH Desktop toolkit with separate settings for each feature: a selection toolbar, a floating assistant, and screenshot, long screenshot and screen recording modes opened by global shortcuts from a toolbar at the top of the screen. Screenshots support shapes, pen, arrows, text and numbered markers, mosaic, pin to desktop, saving, and forwarding to a DSH conversation or the system share panel (Windows and macOS); recordings capture an area, a window or a full screen as MP4, GIF or WebM with optional system sound and microphone. Extract text, Translate and Knowledge graph on captures use the OCR tools of dsh-vision-router, which is installed separately (the settings page offers a one-click install). Requires DSH Desktop >=0.2.2-rc.1 <0.3.0-0. The features run in a separate Electron helper process and the plugin does not download Electron: with the installer build of DSH Desktop you must provide a standalone Electron through the electronExecutable setting, the DSH_DESKTOP_TOOLS_ELECTRON environment variable or $DSH_HOME/electron/; a DSH Desktop started from a bare Electron reuses it. System sound recording is not available on Linux.
qianDao-photo-finder-skill
bananaive/qiandao-photo-finder-skill
Find photo candidates from the 2026 Qiandao Lake cycling race by bib number and visible gear, with local helper scripts and album snapshot comparison. Needs the event's photo album link; snapshot comparison uses Python 3.10+, bib OCR is macOS only (Swift and Apple Vision), and the optional gear ranking needs Pillow, PyTorch, Transformers and a local DINOv2 model directory.
dsh-self-learn
jackheather/dsh-self-learn
Learn from Bilibili videos, web pages, local files and live streams: local ASR, on-screen OCR and extractive digests add up to about 1.5KB of text per source, so the model reads a summary instead of a full transcript.
socratic-tutor
icefox12138/socratic-tutor
Socratic tutor tools for DSH: cited retrieval, page images, chapter index, session review, embedded console. Teaching behaviour lives in dsh-socratic-persona.
dsh-computer-use
mount9527/dsh-computer-use
Windows desktop operation layer for DSH: 17 tools for window listing, screenshot plus OCR, UI Automation, keyboard and mouse, file operations and CDP browser control. Non-intrusive by default (UI Automation patterns and window messages, never the physical pointer), irreversible steps go through a native confirmation dialog, Esc or an on-page button stops a running task, and a global lease keeps two sessions from driving the desktop at once.
dsh-plugin-wallpaper-cleanup
jokerkenny00137/dsh-plugin-wallpaper-cleanup
Cleans a Wallpaper Engine workshop folder against a screenshot of your subscriptions: it finds the blue check badges, OCRs the tile titles, matches them to each project.json title, and moves non-subscribed wallpapers to the Recycle Bin. Ships a settings page and a floating modal, and is Windows-only.
ui-locate-mcp
citydirector/ui-locate-mcp
Lightweight local visual grounding engine exposed as agent tools
dsh-local-llm
verson00/dsh-local-llm
Runs the local llama.cpp Qwen3.5-4B from a Settings page — Windows only, NVIDIA GPU (8 GB VRAM handles the 4B Q4) — with start, stop and restart, launch parameters, deployment paths with a presence check, provider-route and compaction-policy sync in the profile patch, a loopback request-capture proxy, and a local_worker tool that hands translation, OCR and video-frame chores to the local model by file path. Needs llama-server.exe (verified on b12069) and Qwen3.5-4B GGUF + mmproj files on disk; video frames also need ffmpeg.
dsh-computer-use
lqq151510/dsh-computer-use
macOS computer use with eight computer_* tools: accessibility-tree and Vision OCR screen reading, actions by element index or visible label that also reach background windows, and CoreGraphics mouse and keyboard events with a resident low-latency daemon for game-grade input sequences; its Swift helpers compile on first use, so there is no runtime dependency.