aiq-deploy
Agent skill from nvidia/skills.
What it does
- Access to clone or update https://github.com/NVIDIA-AI-Blueprints/aiq.
- Git available in the shell.
- One deployment runtime:
- Docker Engine with Docker Compose v2 for the default durable local deployment.
- Python 3.11+ and uv for local process or CLI mode.
- Node.js 20+ and npm for local browser UI development mode.
- kubectl 1.28+, Helm 3.12+, and access to a Kubernetes cluster for Helm mode.
Requirements & configuration
- Credentials stored outside chat. Hosted-model usage requires NVIDIAAPIKEY; web research requires at least
- browser UI mode also uses frontend port 3000. Self-hosted model or RAG deployments may require GPU resources.
- backend. Do not ask the full mode question when aiq-research routed here because a deep research request needs a
- aiq-research needs a reachable AI-Q server URL. If the backend is on the default port, no extra configuration is
- Destructive cleanup, such as deleting Docker volumes, requires explicit user approval.
Configuration: NVIDIA_API_KEYTAVILY_API_KEYSERPER_API_KEYEXA_API_KEYAIQ_SERVER_URLBACKEND_CONFIGCONFIG_FILERAG_SERVER_URL
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
Source
Repository: https://github.com/nvidia/skills
aiq-deploy FAQ
What does the aiq-deploy skill do?
| Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure. Access to clone or update https://github.com/NVIDIA-AI-Blueprints/aiq. Git available in the shell.
What does aiq-deploy require?
Credentials stored outside chat. Hosted-model usage requires NVIDIAAPIKEY; web research requires at least browser UI mode also uses frontend port 3000. Self-hosted model or RAG deployments may require GPU resources. backend. Do not ask the full mode question when aiq-research routed here because a deep research request needs a aiq-research needs a reachable AI-Q server URL. If the backend is on the default port, no extra configuration is Destructive cleanup, such as deleting Docker volumes, requires explicit user approval. Configuration keys: NVIDIA_API_KEY, TAVILY_API_KEY, SERPER_API_KEY, EXA_API_KEY, AIQ_SERVER_URL, BACKEND_CONFIG, CONFIG_FILE, RAG_SERVER_URL.
How do I install aiq-deploy?
Run: npx -y skills add https://github.com/nvidia/skills --skill aiq-deploy --agent claude-code — the source lives at github.com/nvidia/skills.
Maintain aiq-deploy?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[aiq-deploy on getagentictools](https://getagentictools.com/skills/nvidia-skills-aiq-deploy?ref=badge) npx agentictools info skills/nvidia-skills-aiq-deploy The second line is the CLI lookup for this page — handy in READMEs and docs.