Directory
Published directory entries matching your search.
Firecrawl is a web data API designed for AI agents. It allows searching and scraping web content, returning data in formats such as JSON and Markdown. The service also provides access to Alexandria’s providers and specialized indexes. Firecrawl is open source, used by over 150,000 companies, and announced a $75 million Series B funding round.
Impala is a distributed C++ query engine for SQL queries over petabytes of data stored in Apache Hadoop clusters. It supports data in HDFS, Apache HBase and Amazon S3, window functions and subqueries, and uses LLVM for on-the-fly code generation. It is Apache-licensed and open source, and the repository is a mirror of Apache Impala.
MinusX is an open source agentic business intelligence platform that combines a data agent with a BI tool. It answers questions, builds dashboards and sets alerts, with slides and data stories, visualizations and a SQL GUI. It can be self-hosted or used via MinusX Cloud, and the source is available and inspectable.
OpenMetadata is an open-source AI context layer powered by metadata, semantics, and memory that provides a shared, rich understanding of data for people and AI. It was built by the founders of Apache Hadoop, Apache Atlas, and Uber Databook. The unified platform supports data cataloging, discovery, quality, observability, governance, lineage, and collaboration.
RAWGraphs is a free and open source tool for data visualization. It is a web app that offers almost 30 visual models to visualize quantities, hierarchies and time series. Data inserted is processed only by the web browser, and projects can be saved or exported as vector or raster images.
Analyzes structured data and helps produce queries, insights or visualizations.
An open source tool for running arbitrary queries against public data from the Stack Exchange network.
Open CC-BY-4.0 dataset of evidence-graded dietary-supplement data covering dosing, bioavailability, drug-nutrient interactions and cost-per-effective-dose, with every clinical claim tied to a PubMed PMID. Compiled by Verified Supplement Data, it is mirrored on Hugging Face and Kaggle and offered as a free live JSON API.
An article comparing Topological Data Analysis results with those from t-SNE and UMAP packages. It discusses advantages of TDA coupled with self-supervised learning and covers case studies in IoT, image analysis and text analysis, plus open-source libraries for starting with TDA.
Open LLMs is a public repository that curates a list of open large language models (LLMs) available for commercial use. It also includes related datasets for LLM pre-training, instruction-tuning, and alignment-tuning, and is hosted under the eugeneyan GitHub organization.
Open Notebook is an open-source, AI-powered note-taking and research platform focused on user privacy. It includes a podcast generator that transforms notes into customizable audio content, AI tools for summarizing notes and generating insights, granular privacy controls for AI data access, and support for integrating links, PDFs, text files, presentations, YouTube videos and other content types. The platform is designed for researchers, students, and learning enthusiasts.
The Open VLM Leaderboard is an interactive Hugging Face Space that displays the Open VLM main leaderboard and individual dataset leaderboards. Users can filter results by evaluation dimensions, model size, model type and other related criteria.
A GitHub repository for OpenPrompt.co, a project to create, use and share ChatGPT prompts. The repository includes a list of the most starred prompts on OpenPrompt.co, updated every 24 hours, with the data also available in JSON format as TopPrompts.json. It is published under the GPL-3.0 license.
Open-source project that applies AI to data analysis, extraction, visualization, or business intelligence.
Open-source project that applies AI to data analysis, extraction, visualization, or business intelligence.
This is the official blog for Wren AI, which publishes practical guides covering GenBI, text-to-SQL, context layers, AI agents, embedded analytics, and secure self-hosted deployment for data teams. Posts include topics such as the role of context in AI agent performance and migrating open-source Wren projects to the cloud.
CRF++ is an open source implementation of Conditional Random Fields for segmenting and labeling sequential data. It is designed for general purposes and can be applied to NLP tasks such as named entity recognition, information extraction and text chunking. Feature sets can be redefined, and it is written in C++ with STL.
An open-source JavaScript visualization library that streamlines the creation of beautiful and accessible SVG data visualizations.
Dash is an open-source Python library for building data applications and dashboards without requiring JavaScript expertise. It is maintained by Plotly and hosted on the company's public GitHub repository, where users can access source code and contribute to the project.
Deepchecks is an open-source project for validating machine learning models and data from research to production. It includes built-in and custom checks and suites for tabular, NLP and CV validation, CI and testing management, and monitoring of deployed models. Installation is via pip.
Open-source project that applies AI to data analysis, extraction, visualization, or business intelligence.
Open-source project that applies AI to data analysis, extraction, visualization, or business intelligence.
Open-source project that applies AI to data analysis, extraction, visualization, or business intelligence.
DVC (Data Version Control) is an open-source version control system for data science and machine learning projects. It provides a Git-like experience for organizing data, models, and experiments, with free offerings for individual data scientists and enterprise teams.
