Directory
Published directory entries matching your search.
Bread Dataset Viewer is a VS Code extension for viewing and handling large datasets. It opens JSONL, Parquet, CSV, TSV, JSON, and Arrow/Feather files by streaming and lazy-loading data, and provides Cards, Table, and Raw views. It includes 16 production LLM tokenizers from GPT, Claude, Llama, and Qwen for chat completion data.
The primary interface for interacting with OpenAI models, supporting chat, coding, data analysis, research, and agent workflows.
Open-source Python library for data-centric AI that helps clean data and labels by automatically detecting issues in machine learning datasets. It uses existing models to estimate dataset problems that can be fixed to train better models. It runs on Python 3.10+ and works with any model across classification, regression, segmentation and object detection tasks.
ELKI is an open source data mining software written in Java. It focuses on research in algorithms, emphasizing unsupervised methods in cluster analysis and outlier detection, and offers data index structures for performance and scalability. It is designed for researchers and students to extend.
Evidently is an open-source observability framework for machine learning and large language models, hosted on GitHub under the evidentlyai organization. It enables users to evaluate, test, and monitor AI-powered systems and data pipelines, with support for use cases ranging from tabular data processing to generative AI, and includes more than 100 built-in metrics.
FATE (Federated AI Technology Enabler) is an industrial grade federated learning open source framework that enables enterprises and institutions to collaborate on data while protecting data security and privacy. It implements secure computation protocols based on homomorphic encryption and multi-party computation, and provides federated learning algorithms including logistic regression, tree-based algorithms, deep learning and transfer learning.
ML.NET is an open source, cross-platform machine learning framework for .NET. It lets developers build, train, deploy and consume custom models in .NET applications, with data loading from files and databases, data transformations and many ML algorithms. Models can be trained for scenarios such as classification, forecasting and anomaly detection, and TensorFlow and ONNX models can be consumed within the framework.
MLReef is an open source ML-Ops platform for collaborating, reproducing and sharing machine learning work. The repository notes it is no longer supported or updated there, with work continuing on GitLab. Described sections include data management with versioned data hosting, containerized code repositories, experiment tracking and ML pipelines on Kubernetes, cloud or bare metal.
Orange is an open-source machine learning and data visualization toolbox. It offers visual programming in which widgets are placed on a canvas and connected to load datasets and analyze data. It supports interactive visualization methods including box plots, scatter plots, decision trees, hierarchical clustering, heatmaps, MDS, t-SNE and linear projections. Extensions add text mining, network analysis and other specialized capabilities.
ParadeDB is an open-source PostgreSQL extension hosted on GitHub. It adds functionality for application data management, full-text search, vector retrieval and data aggregations to PostgreSQL databases, and is the home of the pg_search extension. The repository includes links to associated documentation, community resources, a blog and a changelog.
Tensor Trust is the source code for a web game and data cleaning pipeline described as a prompt injection attack game that collects data for adversarial ML research. The repository covers the game and pipeline and links to a paper and the game itself.
The Pile is an 825 GiB open source language modelling data set made of 22 smaller high-quality datasets combined together. It is offered as a training set and as a benchmark, and is distributed as jsonlines data compressed with zstandard.
VeritasGraph is an open-source knowledge graph and GraphRAG framework. It supports multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over user data, using nodes, edges, RDF, and linked data. The project runs locally or in the cloud.
xTuring is an open-source project for building, personalizing, and controlling LLMs, covering data pre-processing through fine-tuning. It includes a simple API for data prep, training, and inference, LoRA and low-precision (INT8/INT4) support, and built-in evaluation metrics such as perplexity. Models can run locally or in a private VPC and scale from CPU to multi-GPU.
A guide to MLOps is an open-source tutorial from the Swiss AI Center team that walks engineers and small teams from notebook experiments to production. It covers local training and model evaluation, moving the model to the cloud, serving and deploying, monitoring and maintaining, and labeling data and retraining, using tools such as DVC, Git, GitHub Actions, CML, Docker, BentoML, Fluent Bit, Evidently AI, and Label Studio.
Agents is an open-source framework for data-centric, self-evolving autonomous language agents. It introduces agent symbolic learning, which treats an agent pipeline like a computational graph and uses prompt-based loss, back-propagation and weight updates to train agents. The project also supports optimizing multi-agent systems and was updated to Agents 2.0 with agent learning and evaluation support.
AI Dev Jobs lists open positions for AI developers, covering technologies such as PyTorch, TensorFlow, LLMs, RAG, and computer vision, with salary data and requirements. It also provides a free public REST API and MCP server for AI job search, matching, and candidate-reviewed application preparation.
AILab-CVC/VideoCrafter is an open-source video diffusion model project. Its VideoCrafter2 iteration is designed to overcome data limitations for high-quality video generation, with improvements over the previous version including better motion rendering and concept combination, and supports generic text-to-video generation.
Anaconda is a platform for Python, data science, and AI development. Its core is conda, an open-source package and environment manager that installs software, resolves dependencies, and isolates projects. Two installers are offered: Anaconda Distribution, which bundles conda, Python, Anaconda Navigator, and hundreds of packages, and Miniconda, a minimal base environment. Anaconda Notebooks is a cloud-based JupyterLab environment.
Arize Phoenix is an AI observability and evaluation tool built by Arize AI and the open-source community on OpenTelemetry and OpenInference. It provides tracing for debugging individual runs, evaluations to score output quality, a prompt playground, and datasets and experiments for comparing changes on the same inputs.
autoai is an open-source Python framework for automatic artificial intelligence focused on regression and classification tasks over numerical data. It automates model search, hyper-parameter tuning, and generates high-quality Jupyter Notebook code for resulting models.
Open-source project that provides AI-assisted learning, courses, tutorials, or study support.
Awadb is an AI-native database built for working with embedding vectors. It is available as a public open-source repository on GitHub, where users can access the code, contribute to development, or deploy it locally on Mac OSX or Linux, or run it as a standalone service. The project is designed to support AI applications that rely on vector embedding functionality.
An awesome list of open-source tools for systematic reviews, meta-analysis, and evidence synthesis derived from Evidence Synthesis Tools Directory. It organizes tools under categories such as literature search, text mining and NLP, screening, data extraction, risk of bias, meta-analysis statistics, and visualization and reporting.
