Plugins
Navegue, filtre e instale plugins do DeepSeek-Harness.
106 plugins encontrados
dsh-token-cost
catgrandfa/dsh-token-cost
Painel de gastos de tokens do DeepSeek Harness: totais de hoje e de 7/30 dias, somas por mês, trimestre e ano-calendário, custos separados entre entrada com acerto ou falha de cache e saída, detalhes por modelo e sessão, orçamentos diários e mensais com projeção para o fim do dia, preços de pico/fora de pico, exportação CSV/JSON e relatório CLI sem dependências. Também calcula preços de modelos GLM (Zhipu) e Kimi fornecidos por rotas de terceiros. Fork mantido de olimc2016/dsh-token-meter-panel (MIT, 0.6.7), com painel refeito; usa IDs próprios de linha, rota e slot para instalar junto do original.
dsh-model-usage
ponydevai/dsh-model-usage
Plugin para DSH Web: exibe em tempo real cotas e uso dos provedores de modelos (DeepSeek / GLM Coding Plan / OpenRouter / Kimi Coding Plan + adaptador personalizado).
dsh-vision-better
ethanweave/dsh-vision-better
Relay de visão para modelos somente de texto: um endpoint configurável compatível com GLM analisa imagens anexadas em segundo plano e o modelo original continua respondendo na mesma sessão, sem alterar mensagem, imagem, modelo ou histórico. No DSH padrão é preciso aplicar patches/0001-session-image-admission.patch, pois as imagens são rejeitadas antes do armazenamento. O repositório inclui scripts para aplicar e restaurar.
dsh-paddle-ocr
tenglongbohai/dsh-paddle-ocr
Adiciona visão PaddleOCR a LLMs de texto como Agnes, DeepSeek, MiniMax, GLM e Mimo. Arquivos locais/URLs; cota grátis de 20.000 páginas/dia. Requer token PaddleOCR solicitado (grátis, 1–3 dias úteis).
dsh-llm-bridge
jayden-dang/dsh-llm-bridge
Usa contas de ChatGPT Codex, Claude, Grok, Antigravity, Kimi, GLM, Cursor, Kiro, Copilot, Qwen, ERNIE, Spark, JetBrains, Perplexity, Replit e Cody como provedores de LLM do DeepSeek Harness via OAuth.
dsh-balance-monitor
shawnkung/dsh-balance-monitor
Mostra na barra lateral do DSH Web os saldos selecionáveis de DeepSeek, Kimi, Zhipu GLM e TeamoRouter, com detalhes por provedor, dados de uso e controles de atualização.
dsh-search-hub
lzh3070/dsh-search-hub
Hub de busca configurável para a ferramenta integrada `web_search`: alterna entre a busca nativa oficial do DeepSeek e Zhipu GLM web_search, com gerenciamento de provedores e credenciais em uma aba das configurações.
dsh-web-search-glm
noemm/dsh-web-search-glm
Provider de busca web Zhipu GLM: registra-se como `glm` no seam ctx.web e executa a ferramenta nativa web_search pela API do GLM compatível com Anthropic (cobrança do Coding Plan).
dsh-web-search-zai
kenny2077/dsh-web-search-zai
Busca web para DeepSeek Harness via Z.ai ou Zhipu, com modos de cota MCP do Coding Plan e cobrança pela API REST, cartão de configurações nativo bilíngue e reutilização de ZAI_API_KEY existente.
aura-vision
ck-epsilon/aura-vision
OCR de visão gratuito com reconhecimento adaptativo por blocos para documentos longos e exportação em Markdown/Word/PNG/Excel.
dsh-zai-coding-models
auuduu/dsh-zai-coding-models
Plugin ponte do DeepSeek Harness: expõe os modelos mais novos do plano de codificação Zhipu/Z.AI (ex. glm-5.3) na rota zai-coding-cn antes que o catálogo pi-ai empacotado alcance.
dsh-vision
314857493/dsh-vision
Plugin do DeepSeek Harness: uma rota `deepseek-vision` que declara entrada de imagem e transcreve imagens coladas por meio dos modelos de visão gratuitos Zhipu GLM antes de delegar ao adaptador 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.