Rasa Pro
Conversational AI framework with CALM
Rasa Pro is the licensed distribution of Rasa for chat and voice assistants. With CALM, LLMs interpret user intent while flows define the assistant's steps and live as version-controlled code. Since version 3.14, Rasa can act as an orchestrator for external agents via the A2A protocol: sub agents are registered via an agent card and invoked in flows with a call step; this feature is marked as beta. Rasa Pro targets enterprise developer teams that want to run assistants on their own infrastructure. A free Developer Edition with volume limits is available; enterprise pricing on request.
Good fit if
Focus: Enterprise developer teams running controllable chat and voice assistants themselves
- your project is about Customer service assistants, Voice assistants in contact centers or Internal employee assistants
- someone on your team writes code
Probably not if
- nobody on your team writes code (2/5 for use without developers)
- your team is just getting started with agents (skill level: Advanced)
- there is little time for training (learning curve: steep)
Key figures
- Usable without developers
- 2/5
- Scalability
- 4/5
- Integrations
- 4/5
- Versioning
- 4/5
- Observability
- 3/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Conversational AI framework with CALM
- Licence
- Proprietär (Rasa-Lizenz, Developer Edition kostenlos)
- Pricing
- Freemium / EnterpriseDeveloper Edition free, usable locally or in production: one bot per company, up to 1,000 external or 100 internal conversations per month, community support. Enterprise with full platform access and Premium Support, pricing on request.
- Deployment
- Self-Hosted, Docker, Kubernetes, On-Prem, Cloud
- Models
- OpenAI, Azure OpenAI, Amazon Bedrock, Anthropic, Mistral, Gemini, Cohere, Groq, Together AI, Self-hosted (vLLM, Ollama, Llama.cpp)
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO yes, RBAC yes
- Latest version
- 3.20.3 (PyPI, 09.10.2026)
Key features
- CALM: LLM understanding with defined flows
- Orchestration of external agents via A2A (sub agents, beta)
- Free choice of LLM, including self-hosted models
- Self-hosting with Helm charts for Kubernetes
- Rasa Studio as no-code interface
Typical use cases
- Customer service assistants
- Voice assistants in contact centers
- Internal employee assistants
- Coordinating external agents via A2A
Market notes
Changes to Rasa Pro by email
We let you know when the status, pricing or license of Rasa Pro changes, together with the weekly market notes.
Implementation
Get Rasa Pro implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- Low-codeBotpressBotpress is a platform for chatbots and AI agents with a visual studio, knowledge bases and analytics. The current version runs as Botpress Cloud; parts of the code such as SDKs and integrations are available on GitHub under the MIT license. Agents can be published to websites, WhatsApp, Slack and other channels.View profile
- SpecialisedKore.aiKore.ai is an enterprise platform for AI agents in customer service, for employees and for processes. It offers a visual builder, multi-agent orchestration, support for many languages and integrations with contact center systems. The platform mainly targets regulated industries such as banking and insurance.View profile
- No-codeVoiceflowVoiceflow specializes in voice and chat agents and offers a visual editor for dialogue flows. Product, design and engineering teams work together on one agent and publish it to multiple channels. Knowledge sources for RAG and custom API calls can be connected.View profile
- DeveloperAutoGenAutoGen is an open-source framework from Microsoft Research for multi-agent systems, known for group chats between agents and code execution. With the release of Microsoft Agent Framework 1.0 in April 2026, AutoGen entered maintenance mode: it only receives bug fixes and security updates, and new development happens in Agent Framework. Microsoft recommends Agent Framework for new projects. Independently of Microsoft, the community continues the fork AG2.View profile