Overview
ecosystem.Ai Platform 2.0 (v2.0.1) combines behavioral social science with real-time machine learning and agentic operations so enterprises can score, personalize, and learn from every customer interaction in the moment. Deployed entirely inside your Amazon EKS (Kubernetes 1.37, default LLM model gpt-6-luna) cluster (supporting both AWS Graviton ARM64 and x86_64 AMD64 nodes), subscriber features, models, and interaction data remain inside your cloud perimeter.
COMPLETE CONTAINER ARCHITECTURE:
- ecosystem-workbench2 (Port 5270 UI, 8001 Private API, 8004 Public API, 9090 Offline Scorer - workbench.) - Operator Workbench 2 SPA and FastAPI orchestration layer for Projects, Offer Matrices, Dynamic Engagement, Ontology-mapped queries, Analytics Dashboards (/analytics/), Computational Social Science Network Graphs (/networks/), Spend & Money Personalities, Simulations Lab, Runtime Console, and the Ecosystem Agent.
- ecosystem-server-2 (Port 3001 API, 54445 Embedded MongoDB 9.0 + mongot Vector Search, 54321 H2O AutoML - server.) - Core Java/Spring modeling, feature engineering, EcosystemCode generation, and central metadata/feature store.
- ecosystem-runtime-solo (Port 8091 - Horizontal Pod Autoscaled 1..N replicas - runtime.) - Low-latency Java 25 real-time prediction engine exposing POST /invocations (contextual scoring), POST /response (closed-loop bandit/reward learning), POST /mcp (Model Context Protocol server), and pre/post-score plugins.
- ecosystem-campaign-management (Port 54310 UI, 54311 API - campaign.) - Agentic Campaign Management platform to plan, govern, activate, and measure multi-stage outreach campaigns connected to Workbench 2 and runtime scoring.
- ecosystem-data-agents (Port 54325 UI, 54324 FastAPI/LangGraph API - data-agents.) - Autonomous Data Analysis Agents executing extraction, preparation, categorical, actuarial, personality, recommender, time-series, and financial analytics across MongoDB and Trino.
- ecosystem-notebooks (Port 8010 EcoGentic Conversational Journey Worker, 8000 JupyterHub - notebooks.) - Hosts the EcoGentic multi-channel conversational agent runtime and interactive data science notebooks.
- ecosystem-custom-gpts (Port 54320 UI, 54349 API - custom-gpts.) - Domain-grounded specialist GPT and RAG agents connected to live runtime scoring and knowledge bases.
- ecosystem-domain-catalog (Port 8080 - domain-catalog.) - Governed OWL/SKOS domain ontologies, SHACL validation shapes, and industry semantic overlays (Telco CVM, Banking, Insurance, Retail, Gaming).
- ecosystem-modeling (Port 5174 - code.) - EcosystemCode & UML modeling SPA for PlantUML diagramming, ontology alignment, and full-stack application generation (React/Vue + Node TS/Python FastAPI/Java Spring/C# .NET + MongoDB/PostgreSQL).
- ecosystem-app-builds (Port 9099 Supervisor, 15100-15299 Hosted Apps, plus sandboxed Mongo 8.3 :27017 & Postgres 16 :5432 - builds. & app-.) - Python 3.14 local hosting runtime supervising up to 100 generated full-stack applications.
- trino (Port 8080 internal SQL engine) - Distributed ANSI SQL query engine federated directly over ecosystem-server MongoDB 9.0 (:54445) for cross-collection analytics and ontology queries.
- busybox (1.36-multiarch init container) - Pre-startup readiness gate verifying ecosystem-server (:3001) and embedded MongoDB 9.0 (:54445) before dependent services launch.
Highlights
- Closed-loop real-time decisioning (POST /invocations and POST /response) with MCP support (POST /mcp).
- Complete 12-container multi-arch (ARM64 & AMD64) platform for Kubernetes 1.37 with default LLM model gpt-6-luna: Workbench 2, Server + MongoDB 9.0, Runtime 0.9.7, Campaigns, Data Agents, Notebooks/EcoGentic, Custom GPTs, Domain Catalog, EcosystemCode (code.*), App Builds (builds.* + Mongo/Postgres), and Trino.
- 1-Click AWS CloudFormation UI installer (creates or reuses VPC, EFS, Secrets Manager, EKS 1.37 cluster, and Helm release) or standard Helm deployment.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
- Monthly subscription
- $0.00/month
Vendor refund policy
Our AWS Marketplace application doesn't offer refunds or credits for any used or unused service periods, as costs are incurred based on monthly usage.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Helm chart on Amazon EKS (10-App ARM64 & AMD64)
- Amazon EKS
Helm chart
Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.
Version release notes
Unified 10-app (12-container) multi-arch (ARM64 Graviton + AMD64 x86_64) release for Kubernetes 1.37 with default LLM model gpt-6-luna, adding EcosystemCode Modeling UI (code.) and App Builds Supervisor (builds.) alongside Workbench 2, Server + MongoDB 9.0.8, Runtime 0.9.7, Campaigns, Data Agents, Notebooks, Custom GPTs, Domain Catalog, and Trino.
Additional details
Usage instructions
Option A (1-Click Browser UI Install via AWS CloudFormation - Zero CLI): Open https://console.aws.amazon.com/cloudformation/home#/stacks/create/review?templateURL=https://ecosystempredictors.s3.af-south-1.amazonaws.com/marketplace/2.0.1/aws-eks-cloudformation-2.0.1.yaml&stackName=ecosystem-platform , enter your EcosystemMasterKey, InitialAdminPassword, LLM settings, and NodeArchitecture (arm64 or amd64), and click Create stack. Option B (Existing EKS Cluster via Helm): Configure the parameters below (or pass -f values-amd64.yaml for x86_64 nodes) and install the chart into namespace ecosystem. Sign in to Workbench 2 as admin@ecosystem.ai . Score with POST /invocations and send the outcome to POST /response.
Support
Vendor support
Enterprise support from ecosystem.Ai (Ecogenetic LLC). Email support@ecosystem.ai . Docs: https://developer.ecosystem.ai/docs . Terms:
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.
Similar products
