​
Prerequisites

  • Kubernetes cluster (local or cloud)
  • Helm 3.x installed
  • kubectl configured to access your cluster
  • BeeAI installed for post-deployment configuration
This deployment guide is intended for development and testing environments. We don’t recommend public deployments at this time as the platform is still evolving and lacks production-ready security features like user management and rate limiting.

​
Installation

​
Step 1: Create Configuration File

Create a value file with the minimum configuration: config.yaml: 
# If you want to include agents from the default catalog (change release/tag accordingly):
externalRegistries:
  public_github: "https://github.com/i-am-bee/beeai-platform@v0.2.14#path=agent-registry.yaml"
# Your custom agents as docker images
providers:
  # e.g.
  # - location: ghcr.io/i-am-bee/beeai-platform-agent-starter/my-agent:latest
  - location: <docker-image-id>
# Generate the encryption key:
#  - using UV (https://docs.astral.sh/uv/getting-started/installation/)
#   $ uv run --with cryptography python3 -c 'from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())'
#  - using python3 directly
#   $ python3 -m pip install cryptography # (or use your preferred way to install the cryptography package)
#   $ python3 -c 'from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())'
encryptionKey: "encryption-key-from-command"
features:
  uiNavigation: true
# this requires passing an admin password to certain endpoints, you can disable auth for insecure deployments
auth:
  enabled: true
  admin_password: "my-secret-password"

​
Step 2: Install the Chart

Then install the chart using: 
helm install -f config.yaml beeai oci://ghcr.io/i-am-bee/beeai-platform/beeai-platform-chart/beeai-platform:0.2.10

​
Step 3: Setup LLM

After the beeai-platform becomes ready, it’s necessary to configure the LLM provider. We will use the admin-password you created earlier and your preferred LLM credentials, for example: 
kubectl run curlpod --image=curlimages/curl -it --rm --restart=Never -- curl -X PUT \
  beeai-platform-svc:8333/api/v1/variables \
  -u beeai-admin:my-secret-password \
  -H "Content-Type: application/json" \
  -d '{
    "env": {
        "LLM_API_BASE": "https://api.openai.com/v1",
        "LLM_API_KEY": "sk-...",
        "LLM_MODEL": "gpt-4o"
    }
  }'

​
Use the Platform

Test that the platform is working: 
# port-forward in a separate terminal
kubectl port-forward svc/beeai-platform-svc 8333:8333 &

beeai list
beeai run chat hi

​
Configuration Options

​
Security Settings

The current authentication model is basic and intended for development use. For any deployment beyond local testing, carefully consider your security requirements and network access controls.
For development/testing environments with authentication: 
# config.yaml
auth:
  enabled: true
  admin_password: "use-a-strong-password-here"

# Generate a secure encryption key
encryptionKey: "your-32-byte-base64-encoded-key"
For local testing environments without authentication: 
# config.yaml - INSECURE, for testing only
auth:
  enabled: false

​
Agent Configuration

Include specific agents in your deployment: 
# config.yaml
providers:
  # Community agents
  - location: ghcr.io/i-am-bee/beeai-platform/community/aider:latest
  - location: ghcr.io/i-am-bee/beeai-platform/community/gpt-researcher:latest

  # Official agents
  - location: ghcr.io/i-am-bee/beeai-platform/official/beeai-framework/chat:latest

  # Your custom agents
  - location: your-registry.com/your-team/custom-agent:v1.0.0

​
External Agent Registry

Use the default agent registry instead of specifying individual agents: 
# config.yaml
externalRegistries:
  public_github: "https://github.com/i-am-bee/beeai-platform@v0.2.14#path=agent-registry.yaml"
# Omit the 'providers' section to use only registry agents

​
Management Commands

​
Upgrading

To upgrade to a newer version of the beeai platform, use: 
helm upgrade --install -f config.yaml beeai oci://ghcr.io/i-am-bee/beeai-platform/beeai-platform-chart/beeai-platform:<newer-version>

​
View Current Configuration

helm get values beeai

​
Check Deployment Status

helm status beeai
kubectl get pods
kubectl logs deployment/beeai-platform

​
Uninstall

helm uninstall beeai

​
Troubleshooting

​
Common Issues

Platform not starting: 
# Check pod logs
kubectl logs deployment/beeai-platform

# Check events
kubectl get events --sort-by=.lastTimestamp
Can’t access agents: 
# Verify LLM configuration
kubectl logs deployment/beeai-platform | grep -i llm
Authentication issues: 
# Check if authentication is properly configured
kubectl get secret beeai-platform-secret -o yaml