Conversational AI platform for trustworthy text- and voice-based AI agents
Key Features
Single Agent Human-in-the-Loop Streaming Short-Term Memory Long-Term Memory Plugin System Custom Tools MCP Protocol A2A Protocol Guardrails Self-Hosted Cloud Hosted
Community Feedback
Strengths
- Mature ecosystem
- Strong NLU capabilities
- CALM hallucination resistance
- Large community
Weaknesses
- OSS now in maintenance mode (active dev on Rasa Pro commercial)
- Steep learning curve
- CALM requires rethinking existing approaches
Rasa Details
| Organization | Rasa |
| Organization Type | Company |
| Funding | Series b+ |
| Category | Framework |
| Subcategory | Conversational |
| Deployment | Hybrid |
| Primary Language | Python |
| Runtime | Python 3.9+ |
| License | Apache-2.0 |
| Commercial Use | Permissive |
| Install Command | pip install rasa |
| GitHub Stars | 21,100 |
| GitHub Forks | 4,900 |
| Contributors | 750 |
| Release Cadence | Monthly |
| Maturity | Mature |
| Pricing Model | Open core |
| Free Tier | Apache-2.0 OSS in maintenance mode |
| Self-Hosted Free | Yes |
| Community Size | Large (21k stars, 15k forum, 750+ contributors) |
| Community Activity | Active |
| Sentiment | Positive |
| GPU Required | No |
| Research Date | 2026-03-24 |
Use Cases
- Enterprise chatbots
- Voice assistants
- Customer support automation
- Hallucination-resistant conversational AI
When to Use
Best for: Enterprise conversational AI needing hallucination resistance and self-hosting
Avoid when: Need free actively developed open-source (Pro is commercial)
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a