#165165th of 168 in ML frameworks and libraries
lightautoml
AutoML library for tabular, text, image and time series data
- Stars
- 1.5k
- License
- Apache-2.0
- Last commit
- Dec 2025
- Last release
- Dec 2025
- Language
- Python
1,451 on 21 Apr 20261,483 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
LightAutoML (LAMA) is a Python AutoML library that trains models from a few lines using presets such as TabularAutoML, or from composable pipeline blocks for feature generation, selection, ML algorithms and hyperparameter optimization. It handles tabular, time series, image and text data, and includes an interpretable WhiteBox (AutoWoE) preset and uplift modeling. Install from PyPI with optional nlp, cv and report extras.
Who it is for: Data scientists wanting AutoML baselines on tabular, text or time series data
Strengths
- Preset API trains and predicts on tabular data in a few lines
- Custom pipelines can be assembled from feature, selection and tuning blocks
- Eleven tutorial notebooks cover NLP, uplift, time series, SQL sources and neural nets
- Interpretability tools: WhiteBox preset, ICE/PDP plots, LIME for text
Weaknesses
- Full GPU and Spark pipelines live in separate repositories, described as still in progress
- PDF report generation needs system libraries such as cairo and pango
- Classical AutoML only, with no language-model or agent features
- Some courses and video guides are Russian-only
What it needs
- GPU optional
- Needs cairo, pango, gdk-pixbuf, libffi
- Models: tabular, time series, text, image
Quick answers
Is lightautoml open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does lightautoml need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |