# Palashio/libra

Ergonomic machine learning for everyone.

Repository: https://github.com/Palashio/libra
Canonical: https://ross.abutalabs.com/products/libra
Homepage: http://libradocs.org/
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning, neural-networks, auto-ml
Last push: 2025-08-27T18:25:53+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 39, release rhythm 8, longevity 100
- inputs: {"age_days": 2336, "days_push": 371, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1907, forks 109 (observed 2026-08-28T04:05:52.593128+00:00)

## What it is
Libra is a Python autoML library that lets users build, train, and evaluate machine learning models with one-line natural-language-style queries, handling preprocessing, model selection, and plotting automatically. It wraps Keras, TensorFlow, PyTorch, and Scikit-Learn behind an ergonomic client API aimed at non-technical users.

## Use cases
- train a neural network with one line of code
- automate the end-to-end machine learning pipeline
- build ML models without knowing TensorFlow or PyTorch
- auto-select and tune the best model for my dataset
- run machine learning experiments as a non-technical user
- generate model metrics and plots automatically

## When to choose
- you have little or no ML background and want quick results
- you want automated preprocessing, model building, and evaluation in a few lines
- you want to prototype whether ML fits your workflow before hiring specialists
- you still want access to underlying Keras/Scikit-Learn parameters when needed

## When to avoid
- you need fine-grained control over architectures, training loops, or custom layers
- you need cutting-edge or production-grade ML pipelines with strict reproducibility
- you need actively developed features - the project points users to its successor Nylon
- you work outside Python or need GPU-cluster-scale distributed training

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, llm-training, data-science
- domain: machine-learning, data-science, artificial-intelligence
- platform: python, cross-platform
- tags: auto-ml, neural-networks, keras, tensorflow, scikit-learn, no-code-ml, beginner-friendly, docker

## Member repositories
- Palashio/libra (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:52.593128+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:11:14.731346+00:00, confidence not recorded.
  - readme: https://github.com/Palashio/libra (fetched 2026-08-28T04:05:52.593128+00:00, sha a0cb8e8e11af)
  - homepage: http://libradocs.org/ (fetched 2026-08-29T10:50:22.024353+00:00, sha a654e41d8871)
  - site_page: https://libradocs.org/html/about.html (fetched 2026-08-29T10:50:22.033438+00:00, sha d6fa092b7372)
  - registry_pypi: https://pypi.org/pypi/libra/json (fetched 2026-08-29T10:50:22.035523+00:00, sha 48a1aff67f4b)
- Data as of 2026-08-30T08:39:29.467469+00:00.