Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
106 plugins trouvés
dsh-token-cost
catgrandfa/dsh-token-cost
Panneau des dépenses de tokens pour DeepSeek Harness : totaux du jour et sur 7/30 jours, sommes par mois, trimestre et année civile, coûts séparés entre entrées avec succès ou échec du cache et sorties, détail par modèle et session, budgets quotidiens et mensuels avec projection en fin de journée, tarifs heures pleines/creuses, export CSV/JSON et rapport CLI sans dépendances. Calcule aussi les tarifs des modèles GLM (Zhipu) et Kimi via des routes tierces. Fork maintenu de olimc2016/dsh-token-meter-panel (MIT, 0.6.7) avec panneau réécrit ; ses propres IDs de lignes, routes et emplacements permettent de l’installer à côté de l’original.
dsh-model-usage
ponydevai/dsh-model-usage
Plugin DSH Web : affiche en temps réel les quotas et l’utilisation des fournisseurs de modèles (DeepSeek / GLM Coding Plan / OpenRouter / Kimi Coding Plan + adaptateur personnalisé).
dsh-vision-better
ethanweave/dsh-vision-better
Relais de vision pour modèles uniquement textuels : un endpoint configurable compatible GLM analyse en arrière-plan les images jointes et le modèle initial répond dans la même session, sans modifier message, image, modèle ni historique. Il faut appliquer patches/0001-session-image-admission.patch à un DSH standard, sinon les images sont refusées avant stockage. Le dépôt fournit des scripts d’application et de restauration.
dsh-paddle-ocr
tenglongbohai/dsh-paddle-ocr
Ajoute la vision PaddleOCR aux LLM textuels (Agnes, DeepSeek, MiniMax, GLM, Mimo). Fichiers locaux et URLs ; offre gratuite de 20 000 pages/jour. Nécessite un token API PaddleOCR à demander (gratuit, 1–3 jours ouvrés).
dsh-llm-bridge
jayden-dang/dsh-llm-bridge
Utilisez via OAuth les comptes ChatGPT Codex, Claude, Grok, Antigravity, Kimi, GLM, Cursor, Kiro, Copilot, Qwen, ERNIE, Spark, JetBrains, Perplexity, Replit et Cody comme fournisseurs LLM de DeepSeek Harness.
dsh-balance-monitor
shawnkung/dsh-balance-monitor
Affiche dans la barre latérale DSH Web les soldes sélectionnables de DeepSeek, Kimi, Zhipu GLM et TeamoRouter, avec détails par fournisseur, données d’utilisation et commandes d’actualisation.
dsh-search-hub
lzh3070/dsh-search-hub
Hub de recherche configurable pour l’outil intégré `web_search` : bascule entre la recherche native officielle DeepSeek et Zhipu GLM web_search ; gestion des fournisseurs et identifiants dans un onglet des paramètres.
dsh-web-search-glm
noemm/dsh-web-search-glm
Fournisseur de recherche Web Zhipu GLM : s’enregistre sous `glm` sur le seam ctx.web et exécute l’outil serveur natif web_search via l’API GLM compatible Anthropic (facturation Coding Plan).
dsh-web-search-zai
kenny2077/dsh-web-search-zai
Recherche Web pour DeepSeek Harness via Z.ai ou Zhipu, avec modes quota MCP Coding Plan et facturation API REST, carte de réglages native bilingue et réutilisation d’une ZAI_API_KEY existante.
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-zai-coding-models
auuduu/dsh-zai-coding-models
Plugin passerelle DeepSeek Harness : expose les nouveaux modèles du plan de codage Zhipu/Z.AI (par ex. glm-5.3) sur la route zai-coding-cn avant que le catalogue pi-ai fourni ne les rattrape.
dsh-vision
314857493/dsh-vision
Plugin DeepSeek Harness : une route `deepseek-vision` qui déclare l'entrée d'images et transcrit les images collées via les modèles de vision gratuits Zhipu GLM avant de déléguer à l'adaptateur DeepSeek.
dsh-image-gen
adithyanraj03/dsh-image-gen
Multi-provider image generation and editing for DeepSeek Harness (OpenAI-compatible relays with custom /v1/images/generations endpoints, Gemini, Seedream, DashScope, Grok, GLM, local ComfyUI, subscription accounts), an Excalidraw MIT infinite-canvas studio with click-to-place and selection-to-edit references, and a pro viewer with zoom/pan/pinch, region notes and a markup mode that bakes marks into the pixels and sends normalized coordinates to the model.
dsh-acp-agent
goodjin/dsh-acp-agent
Adds external agents to DeepSeek Harness as model rows - seven presets covering GLM (ZCode), MiniMax, Claude, Codex, Grok, Cursor and Qoder - together with the browser-side roster, per-provider quota pills and a self-report health route. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-quotaline
qianchang927/dsh-quotaline
Composer-dock strip: the selected model's balance (topped-up plus granted) or its rolling 5-hour, weekly and monthly windows across DeepSeek account and API, Moonshot, Kimi Coding, Zhipu and GLM Coding — read from DSH credentials, with the key never leaving the Host. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-usage-panel (bundle)
reoanrudo/dsh-usage-panel
Usage panel for DeepSeek Harness: GLM, opencode go, Codex, Claude, DeepSeek and Command Code subscriptions in one popup, with quota-reset buttons and a peak-hour clock.
dsh-glm-quota
mikajin1206/dsh-glm-quota
GLM Coding Plan quota, as a glm_quota tool, a left-sidebar panel, an always-visible sidebar footer strip, a settings section and a plugin-page card. Reads /api/monitor/usage/quota/limit from open.bigmodel.cn or api.z.ai and shows the REMAINING allowance (100% untouched, 0% exhausted) for the 5-hour and weekly token windows plus the monthly MCP budget, each with a reset countdown. Parses both upstream shapes: CREDIT_LIMIT with unit 3/6, and TOKENS_LIMIT. The key goes to the DSH credential store, not a config file.
dsh-balance-plugin
adithyanraj03/dsh-balance-plugin
Provider-aware account balance chip for the DeepSeek Harness composer dock: DeepSeek, OpenRouter, Moonshot/Kimi, Zhipu/GLM, MiniMax and Alibaba Cloud Token Plan, with peak/off-peak and night-discount countdowns.
dsh-model-router
yunxiao11xie/dsh-model-router
Serial model orchestration: a delegate tool over a built-in catalog of current Chinese-market models (DeepSeek, GLM, Doubao, Hunyuan, MiniMax, MiMo, Kimi, Qwen, GPT). The main agent splits work, picks a model per subtask with a required reason, waits for each result, and falls back to a default model; every route is checked against the Session model-selection policy before a child starts. Needs Plugins → Subagent → Model selection enabled for the routes you want (new sessions only) and each model's provider configured. Uses the same plugin id as other model-router plugins, so install only one of them.
dsh-totonai
zemyao7/dsh-totonai
Account-based access to the ToTonAI gateway inside DeepSeek Harness: sign in or register in the settings panel, use 65 mainstream models (GPT, Claude, Gemini, DeepSeek, Doubao, Grok, GLM), and pick a plan then pay by QR code in the same panel. Upstream API keys stay on the server.
dsh-coding-plan-usage
alvinlui-hk/dsh-coding-plan-usage
Shows Qwen Token Plan, Z.ai GLM Coding Plan and MiniMax Coding Plan quota usage in three cards under Settings → Models, reusing the configured provider API keys for Z.ai and MiniMax and a dedicated browser-window sign-in for Qwen.
dsh-feiyu-vision
xxgj666/dsh-feiyu-vision
Image understanding for DSH: describe an image and read the text in it through Zhipu GLM-4V (needs a Zhipu API key, free tier), with optional person identification through Volcengine Ark and anime-only reverse image search through SauceNAO or trace.moe (each needs its own key); ffmpeg must be installed for GIF/WebP input. Keys and the ffmpeg path are set on the plugin's own settings page.
dsh-reasoning-adapter
hatiaa/dsh-reasoning-adapter
Gives hand-declared models on custom or relay routes a vendor-matched reasoning-effort picker: detects Claude, GPT, DeepSeek, GLM, Kimi, Qwen, Gemini, Grok, Doubao or MiMo from the model id, display name or endpoint host, fills in only the levels that vendor accepts plus the pi-ai compat fields its request format needs, and writes them into the profile config so the Models page reasoning switch turns on. Models you edit or switch off are left alone, and a Models page card hands them back on request.
dsh-tlpro-models
dungcsnd1133/dsh-tlpro-models
Declares two model routes in the llm-pi-ai settings section — a TLPro gateway and Z.ai's GLM-5.3 endpoint — with per-model context windows, output caps and reasoning-effort ladders, so the stock model picker can select and tune them. Requires your own TLPRO_API_KEY and a Z.ai coding-plan ZAI_API_KEY; the patch replaces the whole llm-pi-ai row config.