Rasa: Build, test and ship AI agents
Rasa is an open-source platform for product teams to build, test, deploy and run customer-facing AI agents across voice and text channels.
What is Rasa?
Rasa gives product teams a way to build customer-facing AI agents without starting from scratch. Agents can be designed in code or through a visual builder, then tested with end-to-end checks and simulated conversations in both voice and text. Conversation data is reviewed, tagged and clustered so teams can see what needs fixing. The platform is open and modular, so pieces can be swapped as priorities change, and it can run alongside existing agents. Deployment is self-managed on-premises or in a private cloud, or as a managed service, with channel connectors for web chat, Slack, WhatsApp, email and voice. Enterprise controls such as single sign-on, role-based access control and PII management are included.
Who is Rasa for?
- Product teams building customer-facing AI assistants
- Engineering teams that want to self-host agents and keep control of data
- Enterprises replacing or consolidating multiple chatbots
How much does Rasa cost?
Pricing model: freemium. Always check the vendor’s own pricing page before you buy.
| Plan | Price | What you get |
|---|---|---|
| Free Developer Edition | Free | One bot per company, up to 1000 external conversations/month or 100 internal conversations/month; community forum support |
| Enterprise | Contact sales | Full access to Rasa Platform and Premium Support |
Is Rasa worth it?
Rasa fits teams that want to build and govern customer-facing agents themselves rather than hand the stack to a managed black box
Where Rasa is strong
- Agents can be built in code or in a visual builder on one shared codebase
- Deployment options include self-managed on-premises, private cloud and a managed service
- Testing and evaluation tools cover simulated conversations, version comparison and rollback
Where it falls short
- The free Developer Edition is capped at one bot per company and limited monthly conversations
- Enterprise pricing and plan details are only available by contacting sales
How do you get started with Rasa?
- 01Get the free Developer Edition license and read the documentation
- 02Design an assistant in the visual builder or in code, then test it in the try-your-assistant panel
- 03Run end-to-end checks and simulated conversations before deploying to your chosen channels
Rasa: frequently asked questions
Is Rasa free to use?
There is a free Developer Edition license that can be used locally or in production, limited to one bot per company and up to 1000 external conversations per month or 100 internal conversations per month, with community forum support.
How is Rasa priced for larger deployments?
The Enterprise plan is quoted through sales and includes full access to the Rasa Platform and Premium Support, aimed at large-scale deployments and higher automation rates.
Where can I deploy Rasa?
Deployment modes include self-managed on-premises or private cloud, and a managed service. Kubernetes deployment is supported through Helm.
Which channels can a Rasa agent run on?
One agent can answer across channels such as a hotline, Slack, web chat, WhatsApp and email, using REST and WebSocket channel connectors. An IVR connector to AudioCodes VoiceAI Connect is available as an additional purchase.
Rasa alternatives
The closest tools in our directory, matched on category, focus areas and audience.
Teams deploying multilingual AI agents to messaging and voice channels
| Tool | Best for | Free plan | Starting price | Focus areas |
|---|---|---|---|---|
| Rasa | Teams building and governing customer-facing AI agents in-house | Yes | — | — |
| Agenta | Teams building and operating AI agents they can self-host | Yes | $29/mo | — |
| Gooey AI | Teams deploying multilingual AI agents to messaging and voice channels | Yes | $25/mo | — |
| AgentX | No-code platform to build, tune, deploy, and integrate AI Agent Chatbots in minutes. | Yes | — | — |
| Potpie | Large engineering teams automating debugging, testing and delivery | No | — | — |
| RapidCanvas | Large enterprises building custom AI apps | No | — | — |
| OpenServ | Developers and enterprises adding auditable reasoning to agents | Unknown | — | — |
| Promethia | Research and analysis work that needs multiple coordinated agents | Unknown | — | — |
| Rierino | Enterprise teams building AI agents, backends and composable commerce | Unknown | — | — |
| zgi.ai | Teams building governed, self-hosted AI agents on company data | Unknown | — | — |
| 扣子 | Office teams automating writing, slides, tables and media tasks | Unknown | — | — |

