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

What it solves

Rasa provides a framework for automating text and voice-based conversations, enabling the creation of contextual assistants capable of handling complex, layered dialogues with significant back-and-forth interaction.

How it works

It functions as a machine learning framework that allows developers to build assistants for various channels, including Slack, Facebook Messenger, Telegram, and custom integrations. While the legacy open-source version focused on NLU training, the newer CALM (Conversational AI with Language Models) engine combines LLM fluency for dialogue understanding with strict business logic and "flows" to enforce rules and ensure reliability.

Who it’s for

Developers and engineers building production-ready AI agents and conversational assistants for customer support, banking, telecom, and other business applications.

Highlights

  • Multi-channel support: Integrates with platforms like Slack, Microsoft Bot Framework, and Twilio.
  • CALM Engine: Merges LLM flexibility with deterministic business logic.
  • Flow-based design: Uses logical steps instead of rigid dialogue trees.
  • Inspector tool: Provides real-time visibility into the agent's decision-making process.

Related

  • Project
    TEN-framework/ten-framework

    An open-source framework for building real-time multimodal conversational AI agents with low-latency audio, text, and visual capabilities.

  • Project
    plurai-ai/intellagent

    A multi-agent framework that stress-tests conversational AI agents by simulating thousands of realistic edge-case interactions to uncover failure points and optimize performance.

  • Project
    erthorpabar/pabar_agent_runtime

    An AI agent runtime framework that integrates chat, RAG, and agentic loops to enable professional automation tasks across desktop and mobile platforms.

  • Project
    Shy2593666979/AgentChat

    A modern intelligent dialogue system that enables the creation and management of AI agents with multi-agent collaboration, RAG, and a three-layer memory architecture.

  • Project
    Agenta-AI/agenta

    An open-source workspace for building and running AI agents that can automate work through interactive chat or scheduled background tasks.