explaingit

rasahq/rasa

★ 21,172PythonAudience · developerComplexity · 4/5MaintainedLicenseSetup · moderate

TLDR

Open-source framework for building chatbots and voice assistants that understand user intent and manage multi-turn conversations across platforms like Slack, Facebook, and Telegram.

Mindmap

mindmap
  root((repo))
    What it does
      NLU intent recognition
      Dialogue flow management
      Multi-turn conversations
    Deployment targets
      Slack Messenger
      Telegram Twilio
      Custom channels
    Tech stack
      Python framework
      Poetry dependencies
      Machine learning
    Use cases
      Customer support bots
      Banking assistants
      Telecom agents
    Status
      Maintenance mode
      Hello Rasa newer
      CALM engine focus

Things people build with this

USE CASE 1

Build a customer support chatbot that handles multi-turn conversations and routes to human agents when needed.

USE CASE 2

Create a banking assistant that understands customer intents like balance inquiries and fund transfers across Slack or Telegram.

USE CASE 3

Deploy a telecom support agent that recognizes billing questions and service issues without manual intent training.

USE CASE 4

Prototype a voice assistant that manages complex dialogue flows with explicit business logic rules.

Tech stack

PythonPoetryMachine LearningNLUDialogue Management

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Python environment setup with Poetry and ML dependencies; NLU model training or downloading adds time.

Use freely for any purpose, including commercial use, as long as you include the original copyright notice and license text.

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
How do I set up Rasa to build a chatbot that understands customer intents and manages conversation flow?
Prompt 2
Show me how to train a Rasa NLU model to recognize user intents and extract entities from customer messages.
Prompt 3
How do I deploy a Rasa chatbot to Slack or Telegram and handle multi-turn conversations?
Prompt 4
What's the difference between Rasa Open Source and Hello Rasa with CALM, and which should I use for my use case?
Prompt 5
How do I define dialogue flows and business logic rules in Rasa to control chatbot responses?
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.