Rasa is an open-code platform for enterprise conversational AI agents. This listing delivers a fully licensed dialogue engine, container images, and a Helm chart to deploy in your own infrastructure, on the LLM you choose.
The world's largest banks, telecoms, and healthcare companies run Rasa in production. Rasa is an open-code platform for building and running conversational AI agents in the enterprise. The orchestration architecture you would otherwise assemble yourself ships prebuilt, refined over more than a decade of conversational AI in production. You build agent skills in code, locally and version-controlled; this listing delivers the engine that runs them.
With Rasa, you can orchestrate the full spectrum of dialogue: guided workflows for steps that must follow a defined path, autonomous prompt-based reasoning where they can't be predefined, knowledge retrieval for document-grounded answers, and tool calls into your systems. You decide per agent skill.
Rasa is also architected for observability. At build time, Rasa Inspector, a debug panel, shows you the decision-making behind every test conversation. And in production, every message, action, and memory update lands in the Tracker Store as an event history you own (DynamoDB, PostgreSQL, or Redis), with observability through OpenTelemetry into the monitoring stack you already run.
What you get with this listing:
Production container images and Helm chart, pulled directly from AWS Marketplace ECR
The fully licensed Rasa engine; a license reflecting your agreed terms is issued on purchase
A deployment you own and operate: your Amazon EKS cluster, your existing CI/CD, the LLM you choose
Usage instructions covering prerequisites and installation
Deployment requires supporting infrastructure in your account, such as a PostgreSQL database (for example, Amazon RDS) and Kafka; full prerequisites are in the usage instructions.
Highlights
Rasa is the open-code conversational AI Agent solution for enterprises. It allows you to automate internal and external customer conversations. Established in 2016, Rasa is known for building, deploying, and managing conversational customer experiences.
Rasa comes with a deployable dialogue engine that orchestrates agent skills anywhere on the spectrum from fully guided workflows to fully autonomous, prompt-based reasoning, with built-in patterns for interruptions, corrections, and topic shifts.
Rasa includes more than simply a framework and runtime; it includes collaboration workflows to support teams, including testing, simulation, and evaluation workflows to improve your AI Agents.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
This contract-based listing bills on two separate usage dimensions. You pay by the number of Conversations your agents handle. You also pay by the number of Users. These dimensions are independent and additive, so your cost reflects both your conversation volume and the size of your team. Pricing scales as either measure grows. You commit under a contract term rather than paying hourly or on-demand. This structure lets you align spend with both the activity your AI agents process and how many people work on the platform.
Top-of-mind questions for buyers
What counts as one Conversation for billing purposes?
A conversation is one external exchange session between your AI agent and an end user. Each conversation your agents handle counts toward your billed volume. Internal conversations run by your own employees are tracked separately from external ones.
What counts as one User, and does it differ from a Conversation?
A User is a person who works on the platform, such as developers and team members who build and manage agents. Conversations measure end-user interactions your agents process. Users measure your internal team size. These are distinct, so adding team members affects the Users metric only.
Which dimension drives most of my cost — Conversations or Users?
Both charges bill independently and appear together on your invoice. Conversation volume tends to dominate for agents handling heavy end-user traffic. User charges weigh more when a large team builds and maintains agents but handles lower conversation volume. Your mix determines the balance.
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
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
Rasa Pro Helm chart 2.6.1.
Additional details
Usage instructions
Follow the steps in the 'Pull container images and Helm charts' section below in order to pull the Helm chart, you do not need to pull the container images. Next, follow the steps documented in the README file inside the chart to launch the product.
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.
MaiAgent is an enterprise-grade AI agent platform that enables businesses to build, deploy, and manage intelligent chatbots across multiple channels. Powered by leading LLMs (including GPT-4 and Claude), MaiAgent helps teams automate customer support, internal Q&A, and business workflows 24/7, with no coding required.
Professional implementation and training consulting services for MaiAgent Enterprise AI Agent platform. We help and assist organizations deploy, and optimize AI-powered customer service or AI-powered knowledge management system solutions on AWS infrastructure with comprehensive support and knowledge transfer using MaiAgent.
Airia discovers shadow AI, enforces runtime guardrails across models and agents, and maps compliance evidence to EU AI Act, ISO 42001, and NIST AI RMF.
Kore.ai provides an advanced AI agent platform designed to help enterprises transform work, service, and processes with intelligent automation, orchestration, and AI insights. It enables deployment of AI agents at enterprise scale.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.