dsh-nvidia-cloud-provider
Manifest validNVIDIA NIM cloud provider for DeepSeek Harness with model discovery, tool calling and reasoning stream.
📦 @ai-workspace-lab/dsh-nvidia-cloud-provider
NVIDIA NIM cloud provider plugin for DeepSeek Harness (dsh).
It registers the nvidia-nim provider route, connecting DeepSeek Harness directly to build.nvidia.com through an OpenAI-compatible gateway (https://integrate.api.nvidia.com/v1).
Features
- Coexists Independently: Coexists seamlessly with Ollama Cloud and other providers without route, storage, or UI collisions.
- Auto Model Discovery: Automatically fetches and categorizes available NVIDIA NIM models from
integrate.api.nvidia.com/v1/models. - OpenAI-Compatible Streaming: Full support for tool calling, reasoning/thinking streams, and multi-modal image inputs.
- Smart Rotation & Cooldown: Multi-account pooling with automatic cooldown on 429 rate limits and sticky session support.
- Zero-Restart Credential Management: Update or rotate your
NVIDIA_API_KEYdynamically in settings.
Quick Start
1. Install
dsh plugin add @ai-workspace-lab/dsh-nvidia-cloud-provider
Or install from GitHub directly:
dsh plugin add github:ai-workspace-lab/dsh-nvidia-cloud-provider
2. Configure
Add to your cordis.patch.yml:
- id: llm-nvidia-nim
name: "@ai-workspace-lab/dsh-nvidia-cloud-provider"
config:
apiKeyEnv: NVIDIA_API_KEY # or paste directly in Settings → NVIDIA NIM
3. Usage
- Open DeepSeek Harness Settings → NVIDIA NIM.
- Paste your API key from build.nvidia.com (starts with
nvapi-). - Click Save key and Test connection.
- Select any NIM model (e.g.,
google/gemma-4-31b-it,mistralai/mistral-large-4-1t-a52b) in the chat model picker.
Visual Verification
NVIDIA NIM settings page in DeepSeek Harness Desktop (running alongside Ollama Cloud without collision):

License
Comments
Loading…
Similar plugins
Detects available NVIDIA NIM models, verifies each with a real streaming call, saves the API key in-panel, and one-click configures DeepSeek Harness settings.
★ 1
MIT
JavaScript
dsh plugin --profile web add dsh-nvidia-models-panelby zhz8888
为 DSH 接入 AMD Radeon Cloud 模型 provider,支持逐模型设置思考档位 | Adds AMD Radeon Cloud as a model provider for DeepSeek Harness with per-model reasoning effort levels.
★ 3
MIT
JavaScript
Nov 9, 2026
dsh plugin --profile web add @zhz8888/dsh-radeon-cloud-patcherby Asheblog
Ollama Cloud provider for DeepSeek Harness: one-click provider setup with per-model reasoning-effort control and account usage in the Models page and sidebar.
★ 4
MIT
TypeScript
Nov 14, 2026
dsh plugin --profile web add dsh-ollama-cloudby GooDAnDReaDY
Ollama Cloud LLM provider plugin for DeepSeek Harness (dsh).
★ 0
MIT
TypeScript
Oct 22, 2026
dsh plugin --profile web add @goodandready/dsh-ollama-cloud-providerby 66wjz
DSH 提供商与模型高级管理台 · Provider & model management console for DeepSeek Harness (dsh)
★ 6
↓ 51/wk
MIT
JavaScript
Oct 24, 2026
dsh plugin --profile web add dsh-model-capby NOirBRight
Native Ollama Cloud provider and Web configuration plugin for DeepSeek Harness
★ 9
↓ 13/wk
MIT
TypeScript
Sep 29, 2026
dsh plugin --profile web add dsh-llm-ollama