Overview
LoginUI
LoginUI
Chat UI
Admin Cosole

Product video
OVERVIEW
AGENTIC STAR Basic provides AGENTIC STAR v2.x for existing environments. For new deployments, see AGENTIC STAR Advanced, which adds projects: AI agent workflows with human review steps and a record of every run.
AGENTIC STAR is a comprehensive AI Agent platform delivered as an AWS CloudFormation stack. Deploy a full-stack environment to build, manage, and run AI agents - with monitoring, logging, and enterprise security built in. No manual infrastructure setup required.
KEY FEATURES
- One-Click Deployment: Provisions EKS, RDS PostgreSQL, S3 Storage, VPC, and 23 Kubernetes microservices automatically via nested CloudFormation templates
- AI-Ready Data Stack: Qdrant (vector DB), PostgreSQL with pgvector for embeddings
- LibreChat UI: Web interface for chat, agent configuration, and team management
- Full Observability: Prometheus, Grafana, Loki, Alloy, Container Insights
- Enterprise Security: IAM roles with least privilege, VPC-integrated networking, Keycloak authentication, NGINX Ingress with cert-manager
- LLM Flexibility: Routes LLM inference through LiteLLM, a multiLLM gateway - AWS Bedrock as the native provider plus any LiteLLM-supported model.
- Datadog Integration (Optional): Built-in Datadog support for APM and monitoring
WHAT GETS DEPLOYED
AWS Infrastructure:
- Amazon EKS cluster with System + User node groups (Auto Scaling)
- RDS PostgreSQL 16.6 with pgvector extension (Multi-AZ High Availability)
- Private S3 bucket (application data) and Public S3 bucket (CDN/static content)
- VPC with 3 subnets (1 public + 2 private), NAT Gateway, Elastic IP
- IAM roles and policies with least privilege access
- Bootstrap EC2 instance for automated Helm installation
Kubernetes Applications (23 services):
- Agent Executor, AgenticAI Admin, AgenticAI ExtAPI
- Agent Sandbox Controller
- LibreChat, LibreChat Auth (Keycloak), Keycloak Extensions
- Qdrant
- kube-prometheus-stack (Prometheus + Grafana), prometheus-adapter
- Loki, Alloy (logs + metrics), K8s Monitoring, AgenticAI Observability
- NGINX Ingress, cert-manager, ExtAuth Service, Gate Services
- DB Migration, Init Platform, PVC Lifecycle Manager, AgenticAI Datadog
- Upgrade Controller
PREREQUISITES
- AWS account with IAM permissions to create EKS, RDS, VPC, S3, EC2, IAM, Lambda, Bedrock, and CloudFormation resources
- Minimum vCPU quota for EKS node groups (Standard instances)
- LLM endpoint: AWS Bedrock (recommended), connected via the LiteLLM multiLLM gateway
EXTERNAL DEPENDENCIES
This product downloads the following external dependencies at deployment time:
- kubectl binary from kubernetes.io
- Helm binary from helm.sh
- yq binary from github.com/mikefarah/yq (GitHub)
- Helm charts and installer package from seller-managed object storage
- Container images from a seller-managed container registry
SoftBank Corp. is responsible for the availability, security, and integrity of all external dependencies hosted on seller-managed infrastructure.
VERSIONS
This product provides AGENTIC STAR v2.x. SoftBank Corp. continues to maintain v2.x with bug-fix releases. Environments deployed from this product can be updated within v2.x, but cannot be updated to v3.x. v3.x is provided as a separate product, AGENTIC STAR Advanced. Updating an environment deployed from this product to v3.x by other means, such as manually applying v3.x Helm charts, is not supported.
SUPPORT
Contact SoftBank Corp. for deployment support, documentation, and updates.
Highlights
- For existing AGENTIC STAR v2.x environments, with ongoing bug-fix releases. For new deployments, see AGENTIC STAR Advanced, which adds AI agent workflows with human review
- AI agent platform deployed in your AWS account by one CloudFormation stack: Amazon EKS, RDS for PostgreSQL, S3, and 23 Kubernetes microservices installed automatically with Helm
- Built-in safety and choice of models: Amazon Bedrock Guardrails, Amazon Comprehend PII detection, and Amazon Bedrock models through the LiteLLM multiLLM gateway
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimensions summary
Top-of-mind questions for buyers
Vendor refund policy
No refund policy
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
AGENTIC STAR AMI with CloudFormation (EKS Full Stack)
This delivery option uses nested AWS CloudFormation templates to provision the full AGENTIC STAR platform. The entry-point template (main-template.yaml) orchestrates all nested stacks: VPC with NAT Gateway, Amazon EKS cluster with managed node groups, RDS PostgreSQL 16.6 with Multi-AZ HA, S3 buckets, and an ephemeral Setup Helper EC2 instance that installs 23 Kubernetes microservices via Helm.
A placeholder Marketplace EC2 instance (t3.medium) is provisioned in the public subnet to satisfy AWS Marketplace AMI-based product requirements. This instance does not run any application workload.
External dependencies downloaded at deployment time include Helm binaries and charts from seller-managed object storage, and container images from a seller-managed container registry.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
Version 2.10.2 release of AGENTIC STAR on AWS Marketplace.
This is a maintenance release of the CloudFormation templates. The bundled Helm installer remains at version 2.10.1, so the application itself is unchanged from v2.10.1.
Key changes in this release:
- Updated the default Amazon RDS for PostgreSQL version to 16.14, fixing deployment failures in regions where the previous version is no longer available
- Added a parameter to select the PostgreSQL version (PostgreSQL 16) on the launch page
All existing components from v2.10.1 (EKS with System/User node groups, RDS PostgreSQL 16 with pgvector, Qdrant, Chat UI with Keycloak, Prometheus/Grafana/Loki/Alloy observability, NGINX Ingress, cert-manager, AWS Bedrock integration, optional Datadog APM) remain included.
Additional details
Usage instructions
LAUNCH INSTRUCTIONS
- Subscribe to AGENTIC STAR on AWS Marketplace and click "Continue to Configuration".
- Select "CloudFormation" as the delivery method, choose your AWS Region, and click "Continue to Launch".
- Click "Launch CloudFormation" the AWS CloudFormation console opens with main-template.yaml pre-loaded.
- Fill in the required parameters: Stack name: choose a unique name (e.g., agentic-star-prod) ImageId: pre-filled by AWS Marketplace - do not change EKS node instance types and scaling limits (default: m5.2xlarge, min 2 nodes each group) RDS instance class and credentials (default identifier: marketplace-db) Admin email and password for the platform Primary language (default: ja)
- Acknowledge that CloudFormation will create IAM resources.
- Click "Create stack". Deployment takes approximately 20~30 minutes.
POST-DEPLOYMENT SETUP
After the stack reaches CREATE_COMPLETE:
- Retrieve the EKS cluster name from the CloudFormation Outputs tab.
- Run the kubectl config command shown in Outputs to authenticate with the cluster.
- Verify all 23 microservices are running: kubectl get pods -A
- Access the Chat UI at the URL shown in Outputs.
- Configure your LLM provider through the LiteLLM multiLLM gateway (e.g., AWS Bedrock region) via the platform admin panel.
- Configure Keycloak with your identity provider if required.
For full documentation, refer to the product User Guide.
Resources
Vendor resources
Support
Vendor support
SoftBank Corp. provides support for AGENTIC STAR on AWS through the official inquiry form.
Support Scope:
Assistance with AWS Marketplace deployment and AWS CloudFormation launch issues Guidance for initial configuration and post-deployment setup Documentation for platform administration and operation Support for product updates and security-related notices Troubleshooting for Kubernetes application health and connectivity Guidance on AWS service quotas relevant to Amazon EKS and Amazon RDS resources
How to Get Help:
For deployment issues, initial configuration questions, operational questions, and other product support inquiries, contact SoftBank Corp. using the official inquiry form.
Sizing Guidance:
AGENTIC STAR requires sufficient vCPU service quotas for the Amazon EKS node groups. Ensure that the AWS account has appropriate service quotas for Amazon EKS, Amazon RDS, Amazon VPC, and Amazon EC2 before deployment. Contact support for assistance with capacity planning and service quota requirements. For support inquiries, please contact SoftBank Corp. using the following form: https://www.softbank.jp/biz/contact-us/demand/ai/agentic-star-inquiry/
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.