rasahq/rasa

Analysis updated 2026-06-21

★ 21,153PythonAudience · developerComplexity · 4/5LicenseSetup · hard

Mindmap

mindmap
  root((rasa))
    What it does
      Chatbot framework
      Multi-turn dialogue
      NLU and intent detection
    Tech Stack
      Python
      Poetry
    Use Cases
      Customer support bot
      Voice assistant
      Messenger Slack bot
    Audience
      AI developers
      Product teams
    Deployment
      Messenger Slack Twilio
      Custom channels

mindmap root((rasa)) What it does Chatbot framework Multi-turn dialogue NLU and intent detection Tech Stack Python Poetry Use Cases Customer support bot Voice assistant Messenger Slack bot Audience AI developers Product teams Deployment Messenger Slack Twilio Custom channels

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Build a customer support chatbot for Facebook Messenger or Slack that handles multi-turn conversations using Rasa's dialogue management.

USE CASE 2

Create a Twilio voice assistant with intent recognition and entity extraction using Rasa's NLU pipeline.

USE CASE 3

Prototype a conversational banking or telecom support agent using Hello Rasa's browser playground and ready-made CALM templates.

What is it built with?

PythonPoetry

How does it compare?

	rasahq/rasa	qwenlm/qwen	verl-project/verl
Stars	21,153	21,109	21,107
Language	Python	Python	Python
Setup difficulty	hard	moderate	hard
Complexity	4/5	4/5	4/5
Audience	developer	developer	researcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1h+

Classic framework is in maintenance mode, requires training NLU models and configuring dialogue flows, consider Hello Rasa for new projects.

Apache License 2.0, use freely for any purpose including commercial projects, modify and distribute freely, as long as you include the license notice.

In plain English

Rasa is an open-source machine learning framework for building chatbots and voice assistants that can handle complex, multi-turn conversations. With Rasa, you can build conversational assistants that deploy to platforms like Facebook Messenger, Slack, Telegram, Twilio, Microsoft Bot Framework, Mattermost, and custom channels. The classic framework handles Natural Language Understanding (NLU) for recognizing user intents and entities, and dialogue management to control the flow of the conversation. The README notes that Rasa Open Source is currently in maintenance mode, and the team's focus has shifted to a newer product called Hello Rasa, which uses their CALM (Conversational AI with Language Models) engine. CALM combines LLM-based dialogue understanding with explicit business logic flows, removing the need to define intents and train NLU models manually. Hello Rasa is an interactive browser-based playground for prototyping agents, with templates for banking, telecom, and support use cases. The classic Rasa Open Source framework is still available and documented, built with Python using Poetry for dependency management. It is Apache License 2.0 licensed.

Copy-paste prompts

Prompt 1

I want to build a Rasa chatbot that handles returns and order status questions. Help me define the intents, entities, and stories I need, and show me how to train and test the model locally.

Prompt 2

Using Rasa's NLU pipeline, how do I add a custom entity extractor for product names that aren't in standard dictionaries?

Prompt 3

I have a Rasa bot and I want to deploy it to Slack. Walk me through configuring the Slack connector and handling the credentials.

Prompt 4

What is the difference between the classic Rasa Open Source framework and the new Hello Rasa CALM engine, and when should I choose one over the other for a new project?

Frequently asked questions

What is rasa?

An open-source Python framework for building chatbots and voice assistants with multi-turn conversation handling, now in maintenance mode as the team focuses on a newer LLM-powered product called Hello Rasa.

What language is rasa written in?

Mainly Python. The stack also includes Python, Poetry.

What license does rasa use?

Apache License 2.0, use freely for any purpose including commercial projects, modify and distribute freely, as long as you include the license notice.

How hard is rasa to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is rasa for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub rasahq on gitmyhub

Verify against the repo before relying on details.