Rasa NLU: Open source language understanding for bots

A drop-in replacement for popular NLP tools like wit.ai, api.ai or LUIS

Language understanding for your bot

Rasa NLU is an open source tool for intent classification and entity extraction. You can think of it as a set of high level APIs for building your own language parser using existing NLP and ML libraries.

  • As seen on:
  • As seen on TechCrunch
  • As seen on BBC
  • As seen on Product Hunt
  • As seen on Bloomberg

Why should you use Rasa?

Own your data

Don't hand it all to a big tech company


Runs locally - no https requests required.


Tune models and get higher accuracy.

Use Cases

Rasa works for all bots

From startups to big corporates, Rasa NLU works for just about any bot use case. But it's particularly well suited to these industries:

  • Insurance

  • Banking

  • Telecoms

  • Travel
A demo of how Rasa NLU works

Open source for better bots

Building a bot MVP is easy , but good conversational software is hard.

Understanding what your users want is hard, steering conversations is hard, handling edge cases is hard, designing conversations is hard, finding compelling use cases is hard.

The pace of innovation in ML is phenomenal and that’s largely due to open access, open source code, and open data. We believe the bot builder community should embrace that spirit.

That's what Rasa is all about.

Why leading bot developers love Rasa

Get tips and tricks on how to build better bots

The Rasa newsletter features the latest updates, case studies, tips, and tricks from the community on how to build better bots. We won't spam you. :-)

How to work with Rasa

Leading developers and enterprises worldwide use Rasa to build the next-generation of bots and assistants.


Learn more about Rasa NLU, Rasa Core or just start building.


Tell us about what you want to build and we'll evaluate how we can help.