microsoft/FLAML

Health v2 · maintenance only

Adoption not part of the score

4390 stars · 561 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

machine-learning llm-training data-science benchmarking machine-learning data-science large-language-models artificial-intelligence python cross-platform automl hyperparameter-optimization model-selection tabular-data time-series-forecasting scikit-learn tuning low-compute

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/FLAML")