Rasa
A self-hosted AI agent platform for text and voice, with business rules, conversation testing, and a shared visual and code workspace.
Rasa is an AI agent platform for product teams building customer-facing text and voice assistants. Teams can deploy agents on their own infrastructure and choose their models and data arrangements. Its CALM engine combines language model understanding with business flows whose code enforces rules, so an assistant can handle conversational wording while following defined processes.
The platform covers development, evaluation, and monitoring. Teams can test agents against simulated voice and text conversations, compare versions, and run end-to-end checks before deployment. Conversation analysis tags and groups findings for review, while decision traces and audit trails help teams investigate agent behavior. One agent can serve a hotline, Slack, web chat, WhatsApp, and email.
Studio gives product teams a visual workspace for building and reviewing agents, with changes stored as code in a shared repository. Developers can work in that same codebase through their IDE, CLI, and SDKs. Rasa MCP Tools connect coding agents to the repository for automated builds, tests, and reviews. The modular platform can work alongside existing agents or provide the base for a team's agent development.
Hello Rasa is a browser playground for prototyping CALM agents, with a copilot for code and flow debugging and export to the Rasa Platform. The separate classic Rasa Open Source framework is Python software under the Apache 2.0 license and is in maintenance mode. It provides language understanding and dialogue management for contextual text and voice assistants.
