Deployment Architecture

Guide

Deploy AKIOS Pro self-hosted beside your existing agent stack. Evidence stays in your infrastructure — VPC, on-prem, or air-gapped.

System Model#

Deployment ArchitectureSidecar model

Your Infrastructure

Agent Stack

LangChain · CrewAI

LLM Gateway

OpenAI · Anthropic

SIEM

Splunk · Sentinel

→

AKIOS Pro

Evidence Collector

Traces · Tool Events

PII Detection

50+ patterns · 7 categories

Control Mapping

EU AI Act · GDPR · SOC 2

Export Engine

JSON · HTML · PDF · SIEM

Self-hosted · Zero egress · Your data stays inside

Sidecar

AKIOS Pro runs beside your LLM gateway and tool infrastructure. It observes without intercepting the execution path.

Your Infrastructure

All evidence — traces, findings, exports — stays inside your VPC, on-prem environment, or air-gapped network.

No Execution Ownership

AKIOS Pro does not run your agents, orchestrate workflows, or replace your existing stack. It monitors and records.

Docker Compose#

Recommended for evaluation and mid-scale production deployments. AKIOS Pro runs as a single service with local volume storage.

docker-compose.yml

version: '3.8'
services:
  akios-pro:
    image: akioudai/akios-pro:latest
    ports:
      - "8080:8080"
    volumes:
      - akios-data:/data
    environment:
      - AKIOS_LICENSE_KEY=${AKIOS_LICENSE_KEY}
      - AKIOS_RETENTION_DAYS=30
      - AKIOS_STORAGE_PATH=/data
    restart: unless-stopped

volumes:
  akios-data:

Volumes

• akios-data: evidence storage
• /data: trace, finding, export persistence

Environment

• AKIOS_LICENSE_KEY: your evaluation license
• AKIOS_RETENTION_DAYS: evidence retention period

Kubernetes#

For enterprise deployments requiring auto-scaling, rolling updates, and service mesh integration.

deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: akios-pro
  labels:
    app: akios-pro
spec:
  replicas: 2
  selector:
    matchLabels:
      app: akios-pro
  template:
    metadata:
      labels:
        app: akios-pro
    spec:
      containers:
      - name: akios-pro
        image: akioudai/akios-pro:latest
        ports:
        - containerPort: 8080
        env:
        - name: AKIOS_LICENSE_KEY
          valueFrom:
            secretKeyRef:
              name: akios-pro-secrets
              key: license-key
        - name: AKIOS_RETENTION_DAYS
          value: "90"
        volumeMounts:
        - name: evidence-storage
          mountPath: /data
        resources:
          requests:
            memory: "2Gi"
            cpu: "500m"
          limits:
            memory: "4Gi"
            cpu: "2"
        livenessProbe:
          httpGet:
            path: /health
            port: 8080
          initialDelaySeconds: 30
          periodSeconds: 15
      volumes:
      - name: evidence-storage
        persistentVolumeClaim:
          claimName: akios-pro-evidence

Kubernetes considerations

Use persistent volumes for evidence retention. For air-gapped environments, ensure the image is available in your private registry. AKIOS Pro does not require external network access after deployment.

Air-Gapped Deployment#

AKIOS Pro is designed for zero-trust and air-gapped environments. No external API calls, no telemetry, no cloud dependencies.

No Egress Required

AKIOS Pro does not phone home. All evidence processing, retention, and export is local.

Offline License Validation

License keys are validated at startup with optional offline activation for air-gapped networks.

Local Storage Only

All traces, findings, and exports reside on local or networked storage inside your security perimeter.

Evidence Retention#

Configure how long AKIOS Pro retains traces, findings, and export history. Retention is enforced at the storage layer and can be customized per environment.

bash

# Set retention to 90 days
docker exec akios-pro akios retention set --days 90

# Check current retention and usage
docker exec akios-pro akios retention status
# Retention: 90 days
# Current usage: 12.4 GB / 50 GB
# Oldest record: 2026-02-03

Next Steps#

Self-Hosted Evaluation

Walk through the evaluation process step by step

Evidence Model

Understand trace records, findings, and control mapping