Extract meaning from messages
Turn free-form text in any language into structured data. Supports single and multiple intents and both pre-trained and custom entities. Fully customizable NLU for any domain.

Rasa Open Source is a framework for natural language understanding, dialogue management, and integrations. Rasa X is a free toolset used to improve contextual assistants built using Rasa Open Source. Together, they include all the features to create powerful text- and voice-based assistants and chatbots.
Get startedTurn free-form text in any language into structured data. Supports single and multiple intents and both pre-trained and custom entities. Fully customizable NLU for any domain.
Retain important context and hold back-and-forth conversations using machine learning-based dialogue management. Smoothly handle topic changes and stay on track when users switch topics. Seamlessly integrate your business logic.
Generate training data by talking to your assistant and provide feedback when it makes an error. Get visibility into model predictions so you know what to optimize. Bootstrap the conversation-driven development process by sharing your assistant with test users.
Run your assistant on Slack, Facebook, Google Home, IVR, custom channels, and more. Serve multiple channels with a single assistant.
Use Rasa's custom actions to interact with APIs, databases, and other systems. Connect with knowledge bases, content management systems, and CRMs.
Annotate user messages and turn them into real-world training data. Quickly sift through conversations and uncover insights with a purpose-built toolset for reviewing and filtering conversations.
Track and manage your models: promote to production or easily roll back. Integrate with automated testing and CI/CD.
Ready-to-deploy Docker containers and orchestration to run Rasa on-prem, or via a preferred cloud provider.
We offer Rasa Enterprise for companies needing additional features and SLAs.