Pular para o conteúdo principal

Plugins

Navegue, filtre e instale plugins do DeepSeek-Harness.

32 plugins encontrados

A

dsh-balance

andregoncalves/dsh-balance

Provider-aware account balance chip for the DSH sidebar, showing the active model provider balance for DeepSeek, OpenRouter, Moonshot/Kimi, Zhipu/GLM, and MiniMax, plus DeepSeek peak/off-peak status.

0há 4 diasUso e cobrançaMIT
A

dsh-minimax-usage-pro

andyfan1094/dsh-minimax-usage-pro

Shows MiniMax Token Plan usage in the Settings page through webServer routes and reads either subscription key name from environment or credentials file.

0mês passadoUso e cobrança
O

dsh-kernel-mesh

oppnc/dsh-kernel-mesh

Registers Kimi, Grok, Codex, and MiniMax as DeepSeek Harness model routes, vendor subagent recipes, and kernel_status / kernel_run / kernel_switch tools.

0mês passadoModelos e provedoresMIT
P

dsh-minimax-usage

pan17/dsh-minimax-usage

Shows MiniMax Token Plan usage beside the DSH Web UI model selector with compact 5h/7d bars, click-to-refresh, automatic idle and heartbeat refreshes, and endpoint fallback. Reuses subscription keys configured under Settings → Model and appears only for MiniMax Token Plan providers.

0há 28 diasUso e cobrançaMIT
G

dsh-ai-wallet

gouzijing0821/dsh-ai-wallet

DSH plugin: one-click account balance & quota panel for multiple AI providers (DeepSeek, Zhipu GLM, Z.ai, Moonshot, MiniMax, StepFun, SiliconFlow, OpenRouter, xAI).

0mês passadoUso e cobrançaMIT
C

dsh-mmx

crazyma99/dsh-mmx

MiniMax CLI bridge for DeepSeek Harness (dsh): mmx-backed web search fallback and transparent image understanding, with first-run onboarding and a settings card.

0mês passadoVisão, voz e multimodalMIT
M

dsh-allrouter

mario03690/dsh-allrouter

Register AllRouter as a DSH provider: one base URL and one key for Kimi K3, Claude, GPT, Grok, GLM, DeepSeek, MiniMax-H3. Switch models without managing separate providers; every call reports real cost.

0mês passadoModelos e provedoresMIT
L

dsh-mingmu

lab-sku/dsh-mingmu

明眸 VisionBridge - Ponte visual própria: quando um modelo cego recebe imagens, chama automaticamente um modelo visual para reconhecê-las e devolve o texto reconhecido ao modelo principal; transparente, configurável e sem perdas ao atualizar.

0há 2 mesesVisão, voz e multimodalMIT