RasaHQ /rasa
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
★ 21,384⑂ 4,906👁 348⑃ 6,488● 6,660▤ 254
+1
Daily
+16
Weekly
+33
Monthly
21,384
stars
4,906
forks
348
watchers
6,488
prs
6,660
issues
254
releases
README
Rasa Open Source
🚧 Note: Maintenance Mode 🚧
Rasa Open Source is currently in maintenance mode.
The future of building AI agents with Rasa is Hello Rasa and CALM.
🚀 The Future of Rasa: Hello Rasa
Building reliable AI agents just got easier.
Hello Rasa is our new interactive playground for prototyping AI agents. It combines LLM fluency with the reliability of business logic using our CALM (Conversational AI with Language Models) engine.
Why switch to Hello Rasa?
No setup required: Open the playground, pick a template (Banking, Telecom, Support), and start building in your browser.
No NLU training: We have moved beyond intents. The LLM handles dialogue understanding while you define the business flows.
Built-in copilot: A specialized AI assistant helps you generate code, debug flows, and expand your agent instantly.
Production ready: Hello Rasa is not just a toy. Export your agent to the Rasa Platform when you are ready to scale.
Core concepts
CALM: Combines LLM flexibility with strict business logic. The LLM understands the user; the code enforces the rules.
Flows: Describe logical steps (e.g., collect money, transfer funds) rather than rigid dialogue trees.
Inspector: See real-time decision-making. No black boxes.
👉 Start building for free at Hello Rasa
---
🧠 Join the Agent Engineering Community
We are building a home for people shipping real-world AI agents.
Agent Engineering is evolving faster than any single framework. This is a vendor-neutral space to discuss architectures, memory, orchestration, and safety with builders across the industry.
What you get:
Network: Meet engineers building production agents
Learn: Discuss practical patterns, not just theory
Access: Direct influence on the Hello Rasa roadmap and early access to features
| Channel | Purpose |
| :--- | :--- |
| agent-design | Architectures, reasoning, memory, testing |
| showcase | Show your builds, demos, and repos |
| ask-anything | Debugging and workflow questions |
👉 Join the Community
---
Rasa Open Source (Legacy)
Note: The documentation and installation instructions below apply to the classic Rasa Open Source framework. For the latest CALM-based experience, see the Hello Rasa section above.
Rasa is an open source machine learning framework for automating text and voice-based conversations. With Rasa, you can build contextual assistants on:
- Facebook Messenger
- Slack
- Google Hangouts
- Webex Teams
- Microsoft Bot Framework
- Rocket.Chat
- Mattermost
- Telegram
- Twilio
- Your own custom conversational channels
Rasa helps you build contextual assistants that can handle layered conversations with lots of back-and-forth.
📚 Resources
- 🤓 Read the docs
- 😁 Install Rasa
- 🚀 Learn all about Conversational AI
- 🏢 Explore the enterprise platform
Development Internals & Contributing
We are happy to receive contributions. Please review our Contribution Guidelines before getting started.
InstallatTop issues
#13169Feature request: Add self-hosted STT input with FunASR/SenseVoice2 comments · 2026-05-31#13027"await" is missing2 comments · 2024-03-24#13185Model server's response filename header controls the local download path (path traversal)1 comments · 2026-10-08#13187[Security] Automated static analysis findings for RasaHQ/rasa (academic research)0 comments · 2026-10-21#13183Twilio, Twilio Voice, Mattermost, and RocketChat channels process inbound webhooks without verifying they originate from the platform0 comments · 2026-10-07#13182Add DemonRoute as a tested `api_base` example in LLM configuration docs?0 comments · 2026-09-30#13179EvalPort adapter for `rasa test nlu` results (intent_report.json / intent_errors.json)0 comments · 2026-08-23#13175Recipe: Cross-session episodic memory via Dakera in Rasa custom actions0 comments · 2026-07-01
Latest release
3.6.21 3.6.21 2025-01-14Rasa 3.6.21 (2025-01-13) Bugfixes - 1424: Replace pickle and joblib with safer alternatives, e.g. json, safetensors, and skops, for serializing components. Note: This is a model breaking change. Please retrain your model. If you have a custom component that inherits from one of the components listed below and modified the persist or load method, make sure to update your code. Please contact us in case you encounter any problems. Affected components: - CountVectorFeaturizer - LexicalSyntacticFeaturizer - LogisticRegressionClassifier - SklearnInten