Meta Learning Python Packages

pyglove

Manipulating Python Programs

openml

OpenML's Python API for a World of Data and More 💫

torchmeta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

paddlefsl

FSL-Mate: A collection of resources for few-shot learning (FSL).

torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

activations

AReLU: Attention-based-Rectified-Linear-Unit

learn2learn

A PyTorch Library for Meta-learning Research

neuralprocesses

A framework for composing Neural Processes in Python

pymfe

Python Meta-Feature Extractor package.

tasksource

Datasets collection and preprocessings framework for NLP extreme multitask learning

easyfsl

Ready-to-use PyTorch code to boost your way into few-shot image classification

redco

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference

simplemaml

A simple generic (TensorFlow) function that implements the MAML algorithm for regression problems as designed by Chelsea Finn et al. 2017

deeppipe-api

DeepPipe efficiently optimizes Machine Learning Pipelines using meta-learning.

featureiq

A knowledge graph and meta-learning framework for context-aware automated feature engineering

aegis5

Aegis-5: Adaptive hybrid ensemble framework for intrusion detection in Industry 5.0 — ACM TAAS 2026

betty-ml

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

pykale

Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for interdisciplinary research, part of the 🔥PyTorch ecosystem. ⭐ Star to support our work!

xenoverse

Benchmarking general decision-making with open & random worlds

rlschool

RLSchool: Excellent environments for reinforcement Learning benchmarking

metafedot

Framework for meta-optimisation in AutoML tasks

disco-torch

A PyTorch port of DeepMind's Disco103 — the meta-learned reinforcement learning update rule from Discovering State-of-the-art Reinforcement Learning Algorithms (Nature, 2025).

metavisionary

Meta Learning (ProtoMAML) Package

dataset2vec

Package for training and further usage of Dataset2Vec meta-model.