Alternatives

Torchmetrics alternatives for AI agents.

Compare similar skills by workflow fit, trust score, quality, GitHub adoption, maintenance, and install readiness.

Current skill

Torchmetrics

Machine learning metrics for distributed, scalable PyTorch applications.

100
Quality
89
Trust
2.4K
Stars
#1

Pytorch Lightning

Similarity 165Trust 93Excellent 100

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

31K starsJun 10, 2026 pushml-automationPythonMachine Learning
$ npx skills add Lightning-AI/pytorch-lightning
#2

Keras

Similarity 157Trust 92Excellent 100

Deep Learning for humans

64K starsJun 12, 2026 pushml-automationPythonMachine Learning
$ npx skills add keras-team/keras
#3

Darts

Similarity 155Trust 92Excellent 100

A python library for user-friendly forecasting and anomaly detection on time series.

9.4K starsJun 6, 2026 pushml-automationPythonMachine Learning
$ npx skills add unit8co/darts
#4

Pyro

Similarity 147Trust 91Excellent 100

Deep universal probabilistic programming with Python and PyTorch

9.0K starsJun 5, 2026 pushml-automationPythonMachine Learning
$ npx skills add pyro-ppl/pyro
#5

Bitsandbytes

Similarity 147Trust 90Excellent 100

Accessible large language models via k-bit quantization for PyTorch.

8.3K starsJun 15, 2026 pushml-automationPythonMachine Learning
$ npx skills add bitsandbytes-foundation/bitsandbytes
#6

TabPFN

Similarity 146Trust 87Excellent 100

⚡ TabPFN: Foundation Model for Tabular Data ⚡

7.4K starsJun 16, 2026 pushml-automationPythonMachine Learning
$ npx skills add PriorLabs/TabPFN
#7

Fastai

Similarity 143Trust 90Excellent 100

The fastai deep learning library

28K starsMay 20, 2026 pushml-automationJupyter NotebookMachine Learning
$ npx skills add fastai/fastai
#8

Ray

Similarity 142Trust 94Excellent 100

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

43K starsJun 16, 2026 pushml-automationPythonMachine Learning
$ npx skills add ray-project/ray
#9

Yolov5

Similarity 141Trust 92Excellent 100

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

58K starsJun 12, 2026 pushml-automationPythonMachine Learning
$ npx skills add ultralytics/yolov5
#10

SpaCy

Similarity 141Trust 90Excellent 100

💫 Industrial-strength Natural Language Processing (NLP) in Python

34K starsMay 19, 2026 pushml-automationPythonMachine Learning
$ npx skills add explosion/spaCy
#11

Pytorch

Similarity 141Trust 88Excellent 100

Tensors and Dynamic neural networks in Python with strong GPU acceleration

101K starsJun 16, 2026 pushml-automationPythonMachine Learning
$ npx skills add pytorch/pytorch
#12

Vision

Similarity 140Trust 92Excellent 100

Datasets, Transforms and Models specific to Computer Vision

18K starsJun 15, 2026 pushml-automationPythonMachine Learning
$ npx skills add pytorch/vision
#13

Learning

Similarity 140Trust 89Excellent 100

A log of things I'm learning

6.9K starsMay 31, 2026 pushml-automationMachine LearningClaude Code
$ npx skills add amitness/learning
#14

Stable Baselines3

Similarity 140Trust 93Excellent 100

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

13K starsJun 15, 2026 pushml-automationPythonMachine Learning
$ npx skills add DLR-RM/stable-baselines3
#15

Nltk

Similarity 140Trust 92Excellent 100

NLTK Source

15K starsJun 11, 2026 pushml-automationPythonMachine Learning
$ npx skills add nltk/nltk
#16

Optuna

Similarity 140Trust 92Excellent 100

A hyperparameter optimization framework

14K starsJun 12, 2026 pushml-automationPythonMachine Learning
$ npx skills add optuna/optuna

How to choose

When should you switch?

Use an alternative when it has a clearer install path, higher trust score, fresher maintenance, or better platform fit for your current agent stack. Keep Torchmetrics if it already passes your workflow test and repository review.

Next step

Compare top candidates side by side

Open the compare page, test the install commands in a sandbox, and check each repository before using a skill in production.