How do I install the Agenticx Deployer skill?

Run npx skillmds@latest add opencue/agenticx-deployer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agenticx Deployer safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agenticx Deployer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agenticx Deployer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agenticx Deployer?

opencue (@opencue) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agenticx Deployer by opencue — Agent Skill

Name: Agenticx Deployer
Author: opencue

Agenticx Deployer

Guide for deploying AgenticX agents to production including Docker containerization, Kubernetes orchestration, Volcengine AgentKit cloud deployment, and API server setup. Use when the user wants to deploy agents, containerize applications, set up Kubernetes, configure cloud deployment, or run the AgenticX API server in production.

opencue Updated Sep 21, 2026

File contents

AgenticX Deployer

Guide for taking AgenticX agents from development to production.

Deployment Options

Method	Best For	Command
API Server	Quick deployment, development	`agx serve`
Docker	Single-node, reproducible	`agx deploy docker`
Kubernetes	Multi-node, auto-scaling	`agx deploy k8s`
Volcengine	Cloud-native, managed	`agx volcengine deploy`

API Server

Start Server

# Default (0.0.0.0:8000)
agx serve

# Custom port + host
agx serve --port 9000 --host 127.0.0.1

# Development with auto-reload
agx serve --port 8000 --reload

Requires: pip install "agenticx[server]"

Health Endpoints

Endpoint	Purpose
`GET /health`	Comprehensive health check
`GET /health/live`	Liveness probe
`GET /health/ready`	Readiness probe
`POST /tasks/submit`	Submit a task

Docker Deployment

Prepare & Build

# Prepare deployment package
agx deploy prepare --output ./deploy-package

# Build Docker image
agx deploy docker --tag my-agent:latest

# Run container
docker run -p 8000:8000 \
  -e OPENAI_API_KEY="sk-..." \
  my-agent:latest

Custom Dockerfile

FROM python:3.11-slim

WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY . .

EXPOSE 8000
CMD ["agx", "serve", "--port", "8000"]

Kubernetes Deployment

# Generate K8s manifests
agx deploy k8s --output ./k8s-manifests

# Apply to cluster
kubectl apply -f ./k8s-manifests/

Generated manifests include:

Deployment with health probes
Service (ClusterIP)
ConfigMap for non-sensitive config
Secret template for API keys
HPA for auto-scaling

Volcengine AgentKit

Cloud-native deployment on Volcengine's managed platform.

Requires: pip install "agenticx[volcengine]"

Setup

# Initialize project
agx volcengine init

# Configure credentials
agx volcengine config \
  --access-key YOUR_AK \
  --secret-key YOUR_SK \
  --region cn-beijing

Deploy

# Deploy agent
agx volcengine deploy --agent my-agent

# Check status
agx volcengine status

# Invoke deployed agent
agx volcengine invoke --agent my-agent --input "Analyze this data"

# Tear down
agx volcengine destroy --agent my-agent

Integration Info

agx volcengine info

Monitoring in Production

# Start monitoring service
agx monitor start

# Check monitoring status
agx monitor status

AgenticX supports Prometheus metrics export for production monitoring.

Pre-Deployment Checklist

Environment variables — all API keys set and not hardcoded
Health probes — /health/live and /health/ready configured
Resource limits — CPU/memory limits set in K8s/Docker
Logging — structured logging enabled
Secrets — use K8s Secrets or vault, never commit keys
Testing — run agx test before deploying
Validation — run agx validate config.yaml for config correctness

---name: agenticx-deployerdescription: Guide for deploying AgenticX agents to production including Docker containerization, Kubernetes orchestration, Volcengine AgentKit cloud deployment, and API server setup. Use when the user wants to deploy agents, containerize applications, set up Kubernetes, configure cloud deployment, or run the AgenticX API server in production.---# AgenticX DeployerGuide for taking AgenticX agents from development to production.## Deployment Options| Method | Best For | Command ||--------|----------|---------|| API Server | Quick deployment, development | `agx serve` || Docker | Single-node, reproducible | `agx deploy docker` || Kubernetes | Multi-node, auto-scaling | `agx deploy k8s` || Volcengine | Cloud-native, managed | `agx volcengine deploy` |## API Server### Start Server```bash# Default (0.0.0.0:8000)agx serve# Custom port + hostagx serve --port 9000 --host 127.0.0.1# Development with auto-reloadagx serve --port 8000 --reload```Requires: `pip install "agenticx[server]"`### Health Endpoints| Endpoint | Purpose ||----------|---------|| `GET /health` | Comprehensive health check || `GET /health/live` | Liveness probe || `GET /health/ready` | Readiness probe || `POST /tasks/submit` | Submit a task |## Docker Deployment### Prepare & Build```bash# Prepare deployment packageagx deploy prepare --output ./deploy-package# Build Docker imageagx deploy docker --tag my-agent:latest# Run containerdocker run -p 8000:8000 \ -e OPENAI_API_KEY="sk-..." \ my-agent:latest```### Custom Dockerfile```dockerfileFROM python:3.11-slimWORKDIR /appCOPY requirements.txt .RUN pip install --no-cache-dir -r requirements.txtCOPY . .EXPOSE 8000CMD ["agx", "serve", "--port", "8000"]```## Kubernetes Deployment```bash# Generate K8s manifestsagx deploy k8s --output ./k8s-manifests# Apply to clusterkubectl apply -f ./k8s-manifests/```Generated manifests include:- Deployment with health probes- Service (ClusterIP)- ConfigMap for non-sensitive config- Secret template for API keys- HPA for auto-scaling## Volcengine AgentKitCloud-native deployment on Volcengine's managed platform.Requires: `pip install "agenticx[volcengine]"`### Setup```bash# Initialize projectagx volcengine init# Configure credentialsagx volcengine config \ --access-key YOUR_AK \ --secret-key YOUR_SK \ --region cn-beijing```### Deploy```bash# Deploy agentagx volcengine deploy --agent my-agent# Check statusagx volcengine status# Invoke deployed agentagx volcengine invoke --agent my-agent --input "Analyze this data"# Tear downagx volcengine destroy --agent my-agent```### Integration Info```bashagx volcengine info```## Monitoring in Production```bash# Start monitoring serviceagx monitor start# Check monitoring statusagx monitor status```AgenticX supports Prometheus metrics export for production monitoring.## Pre-Deployment Checklist1. **Environment variables** — all API keys set and not hardcoded2. **Health probes** — `/health/live` and `/health/ready` configured3. **Resource limits** — CPU/memory limits set in K8s/Docker4. **Logging** — structured logging enabled5. **Secrets** — use K8s Secrets or vault, never commit keys6. **Testing** — run `agx test` before deploying7. **Validation** — run `agx validate config.yaml` for config correctness

Frequently asked questions