# microsoft/FLAML

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

Repository: https://github.com/microsoft/FLAML
Canonical: https://ross.abutalabs.com/products/flaml
Homepage: https://microsoft.github.io/FLAML/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: automl, hyperparam, automated-machine-learning, machine-learning, data-science, python, jupyter-notebook, hyperparameter-optimization, random-forest, scikit-learn, deep-learning, natural-language-processing, natural-language-generation, timeseries-forecasting, classification, regression, tuning, finetuning, tabular-data
Last push: 2026-08-25T04:13:54+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 69, longevity 100
- inputs: {"age_days": 2204, "days_push": 8, "days_rel": 128, "gap_med": 61, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4390, forks 561 (observed 2026-08-28T04:08:47.218086+00:00)

## What it is
FLAML is a lightweight Python library for automated machine learning (AutoML) and hyperparameter tuning. It efficiently finds quality models and configurations for tasks like classification, regression, and time-series forecasting with low computational resources, and also supports economical tuning of LLM-based workflows.

## Use cases
- automatically find the best model for a classification dataset
- tune hyperparameters for a scikit-learn pipeline under a time budget
- forecast time series with automated model selection
- reduce cost of tuning LLM inference parameters
- train a regression model with minimal compute
- automate model selection for tabular data in a Jupyter notebook

## When to choose
- you need accurate ML models with limited compute or time budgets
- you want a lightweight AutoML alternative to heavier frameworks
- you need cost-aware hyperparameter optimization with large search spaces
- you work in Python with scikit-learn-style estimators and want easy customization

## When to avoid
- you need deep learning architecture search or end-to-end neural AutoML
- you require a non-Python or distributed Spark-native AutoML solution
- you want the AutoGen multi-agent functionality, which has moved to a separate repository

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-training, data-science, benchmarking
- domain: machine-learning, data-science, large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: automl, hyperparameter-optimization, model-selection, tabular-data, time-series-forecasting, scikit-learn, tuning, low-compute

## Member repositories
- microsoft/FLAML (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:47.218086+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 2026-08-29T18:21:12.767219+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/FLAML (fetched 2026-08-28T04:08:47.218086+00:00, sha cd9b6e578036)
  - homepage: https://microsoft.github.io/FLAML/ (fetched 2026-08-29T09:09:09.388373+00:00, sha 4f07142cbb1f)
  - registry_pypi: https://pypi.org/pypi/flaml/json (fetched 2026-08-29T09:09:09.390932+00:00, sha 6ab9176b253a)
- Data as of 2026-08-30T08:39:29.467469+00:00.