Vai al contenuto principale

Plugin

Sfoglia, filtra e installa i plugin di DeepSeek-Harness.

105 plugin trovati

P

dsh-model-usage

ponydevai/dsh-model-usage

Plugin DSH Web: mostra in tempo reale quote e utilizzo dei provider di modelli (DeepSeek / GLM Coding Plan / OpenRouter / Kimi Coding Plan + adapter personalizzato).

126 giorni faUtilizzo e fatturazioneMIT
E

dsh-vision-better

ethanweave/dsh-vision-better

Relay visivo per modelli solo testo: un endpoint configurabile compatibile con GLM analizza in background le immagini allegate e il modello originale continua a rispondere nella stessa sessione, senza alterare messaggio, immagine, modello o cronologia. Su DSH standard è necessario applicare patches/0001-session-image-admission.patch, altrimenti le immagini vengono rifiutate prima del salvataggio. Il repository include script per applicare e ripristinare la patch.

1mese scorsoVisione, voce e multimodaleMIT
T

dsh-paddle-ocr

tenglongbohai/dsh-paddle-ocr

Aggiunge vision PaddleOCR a LLM testuali (Agnes, DeepSeek, MiniMax, GLM, Mimo). File locali e URL; tier gratuito 20.000 pagine/giorno. Serve token API PaddleOCR da richiedere (gratis, 1–3 giorni lavorativi).

13 mesi faVisione, voce e multimodale
J

dsh-llm-bridge

jayden-dang/dsh-llm-bridge

Usa tramite OAuth gli account ChatGPT Codex, Claude, Grok, Antigravity, Kimi, GLM, Cursor, Kiro, Copilot, Qwen, ERNIE, Spark, JetBrains, Perplexity, Replit e Cody come provider LLM di DeepSeek Harness.

12 mesi faModelli e providerMIT
S

dsh-balance-monitor

shawnkung/dsh-balance-monitor

Mostra nella barra laterale DSH Web i saldi selezionabili di DeepSeek, Kimi, Zhipu GLM e TeamoRouter, con dettagli per provider, dati di utilizzo e controlli di aggiornamento.

110 giorni faUtilizzo e fatturazioneMIT
L

dsh-search-hub

lzh3070/dsh-search-hub

Hub di ricerca configurabile per lo strumento integrato `web_search`: passa dalla ricerca nativa ufficiale DeepSeek a Zhipu GLM web_search e gestisce provider e credenziali in una scheda delle impostazioni.

13 mesi faStrumenti e capacitàMIT
N

dsh-web-search-glm

noemm/dsh-web-search-glm

Provider di ricerca web Zhipu GLM: si registra come `glm` sul seam ctx.web ed esegue lo strumento server nativo web_search tramite API GLM compatibile con Anthropic (fatturazione Coding Plan).

13 mesi faStrumenti e capacitàMIT
K

dsh-web-search-zai

kenny2077/dsh-web-search-zai

Ricerca web per DeepSeek Harness tramite Z.ai o Zhipu, con modalità quota MCP Coding Plan e fatturazione REST API, scheda impostazioni nativa bilingue e riuso di una ZAI_API_KEY esistente.

13 mesi faStrumenti e capacitàMIT
C

aura-vision

ck-epsilon/aura-vision

OCR di visione gratuito con riconoscimento adattivo a riquadri per documenti lunghi ed esportazione in Markdown/Word/PNG/Excel.

13 mesi faVisione, voce e multimodaleMIT
A

dsh-zai-coding-models

auuduu/dsh-zai-coding-models

Plugin bridge DeepSeek Harness: espone i nuovi modelli del piano coding Zhipu/Z.AI (es. glm-5.3) sulla route zai-coding-cn prima che il catalogo pi-ai integrato si aggiorni.

13 mesi faModelli e providerMIT
3

dsh-vision

314857493/dsh-vision

Plugin DeepSeek Harness: una rotta `deepseek-vision` che dichiara l'input di immagini e trascrive le immagini incollate tramite i modelli di visione gratuiti Zhipu GLM prima di delegare all'adattatore DeepSeek.

13 mesi faVisione, voce e multimodaleMIT
A

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.

03 giorni faVisione, voce e multimodaleGPL-3.0
G

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.

03 giorni faModelli e providerMIT
Q

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.

03 giorni faUtilizzo e fatturazioneMIT
R

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.

06 giorni faUtilizzo e fatturazioneMIT
M

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.

05 giorni faUtilizzo e fatturazioneMIT
A

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.

08 giorni faUtilizzo e fatturazioneMIT
Y

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.

012 giorni faStrumenti e capacitàMIT
Z

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.

07 giorni faModelli e provider
A

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.

07 giorni faUtilizzo e fatturazioneMIT
X

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.

015 giorni faVisione, voce e multimodaleMIT
H

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.

017 giorni faModelli e providerMIT
D

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.

015 giorni faModelli e providerMIT
W

dsh-provider-usage

wjw1-evan/dsh-provider-usage

One collapsible sidebar widget stacking OpenCode GO, Command Code and GLM Code Plan quota windows, with reset countdowns, top-up balances, a settings page and a /provider-usage command.

011 giorni faUtilizzo e fatturazioneMIT