Open-source alternatives to Merlion

Nixtla is a time series analysis platform centered on a transformer-based foundation model. It provides zero-shot inference for forecasting and anomaly detection, allowing the system to predict future values for new time series without requiring model retraining. The project is designed for large-scale analysis, using distributed inference scaling and forecast parallelization to process millions of data series. It supports fine-tuning adaptation to adjust pretrained weights for domain-specific datasets and offers deployment options ranging from local execution and private containers to integr

Evals is a framework designed for automating, managing, and executing repeatable benchmarking suites to analyze the quality and performance of language models. It provides a platform for running standardized tests to measure model accuracy and track behavioral changes over time. The system distinguishes itself through a modular architecture that uses a standardized adapter layer to normalize inputs and outputs, allowing different models to be swapped and tested interchangeably. It supports the creation of custom benchmarks using proprietary data, enabling quality assurance on sensitive tasks

statsforecast is a high-performance statistical time series forecasting library designed to generate point forecasts and prediction intervals. It functions as a distributed time series framework that utilizes a C-based forecasting engine and an automated model selector to identify and fit the optimal statistical model for every unique series in a dataset. The system also includes a time series anomaly detector to identify unusual data points by comparing observed values against probabilistic forecast intervals. The project is distinguished by its ability to handle massive-scale parallel forec

Kats is a time series analysis framework and library providing tools for statistical characterization, anomaly detection, and trend forecasting. It functions as a toolkit for predicting future values based on historical data and identifying irregular patterns or structural change points within temporal sequences. The project includes a temporal feature extraction tool to calculate descriptive statistics and characteristics that summarize time series behavior. It also provides a system for model hyperparameter tuning using self-supervised learning to improve the scale and generalization of pre

This PyTorch-based deep learning library provides a framework for analyzing and forecasting temporal data. It implements specialized architectures for time series forecasting, anomaly detection, data imputation, and classification. The project distinguishes itself through the inclusion of zero-shot inference capabilities, allowing large-scale temporal models to be evaluated on unseen datasets without requiring task-specific fine-tuning. The framework covers a broad range of analytical capabilities, including the recovery of missing values in incomplete datasets, the identification of irregul

TimesFM is a time series foundation model designed to generalize across diverse temporal datasets for forecasting and anomaly detection. It functions as a pretrained model for predicting future values in univariate time series data, eliminating the need for manual training from scratch. The project includes a framework for adapting pretrained weights to specific datasets using low-rank adaptation to improve accuracy. It also provides specialized capabilities for integrating time-series predictions as tools within autonomous AI agent architectures and automated workflows. The system supports

NuPIC is a machine learning framework that implements Hierarchical Temporal Memory (HTM) theory, a neuroscience-inspired approach to artificial intelligence. It models principles of the neocortex to build systems capable of learning patterns from streaming data, performing sequence prediction, and detecting anomalies in real-time data streams. The framework is built around a Cortical Learning Algorithm that combines spatial pooling and temporal memory to process streaming input. It uses Sparse Distributed Representations to encode input patterns, a Spatial Pooler to convert dense input into s

PaddleX is a PaddlePaddle-based framework for building, deploying, and fine-tuning AI model pipelines, with pre-built support for computer vision, OCR, document analysis, and time series tasks. It offers a toolkit of ready-to-use pipelines for image classification, object detection, segmentation, and pose estimation, alongside an end-to-end OCR document analysis pipeline that extracts text, tables, formulas, and layout information. The platform also includes a dedicated time series forecasting pipeline for analyzing historical data to detect anomalies, classify patterns, and predict future val

This is a deep learning framework for predicting future values in sequential data using PyTorch architectures. It provides a toolkit for long-horizon and probabilistic time series prediction, incorporating a data pipeline to convert tabular dataframes into sequences for supervised deep learning training. The library utilizes a training wrapper to scale model execution across CPUs and GPUs. It supports the generation of probability distributions for future outcomes instead of single point estimates to quantify prediction uncertainty. The framework includes capabilities for implementing foreca

This repository is a collection of practical deep learning implementations and examples built using the TensorFlow framework. It provides a variety of neural network architectures focusing on natural language processing, recommendation systems, reinforcement learning, and time series prediction. The project features a range of specialized models, including sequence-to-sequence and transformer architectures for text processing, and factorization machines for personalized ranking and retrieval. It also includes implementations of reinforcement learning agents using actor-critic and policy gradi

This project is a structured learning curriculum and technical reference for mastering deep learning with TensorFlow. It provides a comprehensive guide for building, training, and deploying neural networks, combining theoretical fundamentals with practical implementation examples. The repository distinguishes itself by covering the end-to-end machine learning workflow, from low-level tensor mathematics and linear algebra to the creation of complex model architectures. It includes specific guidance on developing data pipelines for diverse data types, such as images, text, and time-series seque

TensorFlow.js is a JavaScript machine learning library used for training and deploying models in web browsers and server-side environments. It functions as a browser-based model trainer, a WebAssembly inference engine, and a WebGPU accelerated tensor library for low-level linear algebra. The project also includes a model converter to transform Python-based models into optimized formats for JavaScript execution. The library distinguishes itself through a pluggable backend architecture that allows mathematical operations to be executed via CPU, WebGL, or WebGPU. It supports the conversion of Py

Mmlspark is a distributed framework for executing machine learning models, data transformations, and AI service integrations across Apache Spark clusters. It functions as a distributed machine learning library and pipeline orchestrator, allowing users to integrate pre-trained cognitive services and custom models into large-scale batch and streaming workflows. The project is distinguished by its ability to incorporate external AI services and web APIs directly into big data pipelines for text and vision analysis. It provides a scalable model training framework that coordinates gradient boostin

AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc

Neuralforecast is a neural time series forecasting library designed to predict future values for one or multiple series using deep learning architectures. It functions as a distributed machine learning forecasting framework that enables the training of global models across multiple time series to improve generalization through cross-learning. The project distinguishes itself as a probabilistic forecasting toolkit that produces uncertainty intervals and probability distributions rather than single point estimates. It also includes a hierarchical forecast reconciler to ensure that predictions a

lmms-eval is a benchmarking system and performance analysis suite designed to measure the capabilities of large multimodal models. It provides a framework for evaluating models across text, image, audio, and video datasets, serving as a multimodal dataset orchestrator and benchmarking tool to quantify accuracy and efficiency. The project distinguishes itself through a unified multimodal message protocol that structures diverse media inputs for consistent model consumption. It features specialized benchmarking for audio, video, visual, document, and spatial reasoning, alongside tools for model

tsai is a deep learning library for time series classification, regression, and forecasting. Built on PyTorch and fastai, it provides a framework for assigning labels to sequential data, predicting future values in univariate or multivariate sequences, and training representations on unlabeled data through self-supervised learning. The library distinguishes itself with specialized temporal engineering and scaling capabilities. It includes tools for cyclical temporal encoding to capture seasonal patterns and online window slicing to process datasets larger than available memory. It also suppor

Neural Prophet is a PyTorch-based time series forecasting library designed for interpretable machine learning. It serves as a decomposition framework that breaks signals into constituent parts such as autoregressive effects, piecewise linear trends, and Fourier-based seasonality to predict future values. The project distinguishes itself by combining neural networks with traditional algorithms to produce forecasts that explain underlying trend drivers. It features a global time series modeling approach, allowing a single model to be trained across multiple simultaneous series to share learned

Stumpy is a Python library for scalable time series analysis centered on the implementation of matrix profile algorithms. It provides a framework for calculating distance profiles to identify repeating patterns and anomalies within time series data. The project is distinguished by its ability to scale heavy computations across GPU hardware and distributed clusters using Dask. It supports multidimensional analysis for discovering motifs across concurrent data streams and offers incremental computation for real-time streaming analysis. The library covers a broad range of time series mining tec

This repository is a collection of reference implementations, templates, and sample galleries for building and integrating machine learning models within the .NET ecosystem. It provides a set of practical demonstrations for implementing machine learning workflows using the ML.NET framework. The project emphasizes the integration of pre-trained models via the Open Neural Network Exchange format, allowing the execution of external machine learning logic within managed applications. It includes specific examples for loading and executing these standardized models to ensure cross-platform compati

GluonTS is a probabilistic time series library and deep learning forecasting framework. It provides a toolkit for building, training, and evaluating neural network architectures that predict future values as probability distributions to quantify uncertainty. The project distinguishes itself by supporting zero-shot forecasting and integrating diverse modeling approaches, including deep probabilistic neural networks and wrappers for external statistical libraries such as Prophet and R forecast. It implements specialized architectural primitives like causal convolutions and invertible residual n

This is a comprehensive deep learning course delivered entirely through Jupyter Notebooks, designed to teach neural network construction using TensorFlow 2.x. The curriculum follows a sequential-model-first pedagogy, introducing the Sequential API before moving to functional and subclassing approaches, and covers the full spectrum of model building from regression and classification through convolutional neural networks, natural language processing, and time series forecasting. The course is structured around a checkpoint-based training workflow that saves the best model weights during traini

AutoGluon is an automated machine learning framework designed to optimize model selection and hyperparameter tuning across tabular, text, image, and time series data. It functions as an ensemble learning library and a tabular data prediction engine, aiming to build high-accuracy predictive models without manual algorithm selection. The framework integrates multimodal machine learning pipelines that combine disparate data types into a single representation using specialized encoders. It also includes a probabilistic time series forecaster that fits multiple statistical and deep learning models

Anomalib is a PyTorch-based library for visual anomaly detection, offering a modular framework, a comprehensive model zoo, and a benchmarking suite designed for industrial defect detection. It provides a wide range of algorithms—including generative, discriminative, teacher-student, and vision-language approaches—that support unsupervised, few-shot, and zero-shot settings. The library enables deployment through model export to ONNX and OpenVINO for edge devices, and includes a no-code web application for training and inference. It also features a command-line interface for orchestrating multi

OpenCompass is a comprehensive evaluation platform, benchmarking suite, and distributed model evaluator designed to measure the performance and accuracy of large language models. It provides a framework for benchmarking both open-source and API-based models against diverse datasets using standardized metrics and reproducible pipelines. The project features an automated judging framework that uses language models as judges to score and verify the quality of generated text. It includes a performance leaderboard system for comparing the relative capabilities of various models across industry-sta

This project is a PyTorch-based framework and toolkit for scene text recognition. It provides a deep learning pipeline for extracting characters and words from images of natural environments, covering the full process from training data preparation to model validation. The framework functions as a standardized benchmark for measuring the accuracy and inference speed of text recognition models. It includes tools for calculating recognition accuracy and measuring GPU processing time per image to evaluate model performance across consistent datasets. The system incorporates visual and sequentia