Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Visualizations and helpers to improve and debug machine learning models for Rasa Open Source
| Date | Stars |
|---|---|
| 2026-07-31 | 309 |
| 2026-08-06 | 309 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
> **Note!** The code for this project is meant for Rasa Open Source 2.x.
<img src="docs/logo.png" width=300 align="right">
# RasaLit
A collection of helpful viewers that help with understand Rasa NLU components.
Some of these views are made using
[streamlit](https://github.com/streamlit/streamlit), hence the wink in the name.
Feedback is welcome.
## Installation
You can install via pip by linking to this github repository.
```
python -m pip install git+https://github.com/RasaHQ/rasalit
```
### Compatibility
The focus is to support the most recent version of Rasa. Current we target 2.x.
We keep older versions around though. You can find rasalit for Rasa 1.10 [here](https://github.com/RasaHQ/rasalit/tree/r1.10).
## Usage
You can directly access the command line app.
```
> python -m rasalit --help
Usage: rasalit [OPTIONS] COMMAND [ARGS]...
Helper Views for Rasa NLU
Options:
--help Show this message and exit.
Commands:
diet-explorer Allows you to explore the DIET settings.
live-nlu Select a trained Rasa model and interact with it.
nlu-cluster Cluster a text file to look for clusters of intents.
overview Gives an overview of all `rasa train nlu` results.
spelling Check the effect of spelling on NLU predictions.
version Prints the current version of rasalit.
```
## Features
The app contains a collection of viewers that each specialize in a seperate task.
### `nlu-cluster`
This command allows you to cluster similar utterances in a text file.
Note that this app has some extra dependencies. You can install them via;
```
python -m pip install "whatlies[umap]"
```
Example Usage:
```
python -m rasalit nlu-cluster --port 8501
```
This will start a server locally. Internally it is using the [whatlies]() package to
handle the embeddings. This means that while the demo is only in English, you can extend
the code to work for Non-English scenarios too! For more details, as well as a labelling tool,
check out the notebook found [here](https://github.com/RasaHQ/rasalit/blob/main/notebooks/bulk-labelling/bulk-labelling-ui.ipynb).
### `overview`
This command shows an summary of the intent/entity scores from a `rasa train nlu` run.
Example Usage:
```
> python -m rasalit overview --folder gridresults --port 8501
```
This will start a server locally on port that will displace an interactive
dashboard of all your NLU gridsearch data.
To fully benefit from this feature you'll need to run some models first.
You can run cross validation of models in Rasa via the command line:
```
rasa test nlu --config configs/config-light.yml \
--cross-validation --runs 1 --folds 2 \
--out gridresults/config-light
rasa test nlu --config configs/config-heavy.yml \
--cross-validation --runs 1 --folds 2 \
--out gridresults/config-heavy
```
Then Rasa, in this case, will save the results in `gridresults/config-light` and
`gridresults/config-heavy` respectively.
To get an overview of all the results in subfolders of `gridresults`,
you can run the `rasalit overview --folder gridresults` command from the same
folder where you ran the `rasa test` command. You'll get some simple charts
that summarise the intent/entity performance.
### `spelling`
This command let's you predict text with augmented spelling errors to check for robustness.
```
> python -m rasalit spelling --help
> python -m rasalit spelling --port 8501
```
This will start a server locally on port 8501 that will displace an interactive
playground for your trained Rasa NLU model. You can see the confidence levels change
as you allow for more or less spelling errors.
It's assumed that you run this command from the root of your Rasa project but you
can also make it point to other projects via the command line settings.
### `live-nlu`
This command gives you an interactive gui that lets you see the output of a Excerpt of 6,373 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bcb9ccaca247277a, llm:Description: 'Visualizations and helpers to improve and debug machine learning models for Rasa Open Source'; README: 'Helper Views for Rasa NLU', commands like 'nlu-cluster', 'diet-explorer', 'live-nlu' and uses streamlit/embeddings for visualization.
matched fp:bcb9ccaca247277a, llm:Description: 'Visualizations and helpers to improve and debug machine learning models for Rasa Open Source'; README: 'Helper Views for Rasa NLU', commands like 'nlu-cluster', 'diet-explorer', 'live-nlu' and uses streamlit/embeddings for visualization.
matched fp:bcb9ccaca247277a, llm:Description: 'Visualizations and helpers to improve and debug machine learning models for Rasa Open Source'; README: 'Helper Views for Rasa NLU', commands like 'nlu-cluster', 'diet-explorer', 'live-nlu' and uses streamlit/embeddings for visualization.