Directory
Published directory entries matching your search.
ANGRYsearch is a Linux file search tool that returns instant results as you type, written in Python 3 with a PyQt5 GUI. It offers lite and full modes, and fast, slow and regex search modes. The database and config files are stored locally; indexing about one million files can take roughly two minutes.
Awesome AutoDL is a curated list of automated deep learning resources and an in-depth analysis, subtitled that neural architecture search is not the end. It collects papers, libraries and benchmarks covering neural architecture search and hyper-parameter optimization.
Faiss is a library for efficient similarity search and clustering of dense vectors, containing algorithms that search sets of vectors of any size. It is written in C++ with complete wrappers for Python/numpy, with some algorithms implemented on the GPU, and is developed primarily at Meta's Fundamental AI Research group.
neuml/txtai is an all-in-one AI framework for semantic search, LLM orchestration, and language model workflows. It is open source and hosted on GitHub. The framework provides tools for building applications that understand and generate text.
pgvecto.rs is an open-source tool that provides scalable, low-latency, hybrid-enabled vector search for PostgreSQL. It is designed to enhance vector search capabilities without modifying the core database system, per its official GitHub repository.
QsarDB is a repository for (Q)SAR/QSPR models and datasets, described as ready for discovery, exploring and citing. It hosts archives of QSARs, QMRFs and chemicals, states that models are represented in accordance with FAIR principles, and supports chemical search by exact structure, similarity and substructure.
Search an online collection of books, documents, media and archival records.
Vald is a highly scalable distributed vector search engine. It is hosted on GitHub and provides documentation on installation using Helm, requirements, and usage. The project focuses on delivering a scalable solution for vector search.
A Hugging Face Space that fetches the README from the Awesome AI Web Search GitHub repository, converts the markdown to HTML and displays it. Opening the site shows the curated list of AI-powered web search software without any upload or typing.
The EU Clinical Trials Register offers a free search of clinical trials in European Union member states and the European Economic Area. Its search engine queries information entered into the EudraCT database, with simple and advanced search modes and filters. It also displays information on EudraCT trials, and ongoing EU/EEA trials are displayed through the Clinical Trials Information System.
MemFree is a hybrid AI search engine and AI page generator. It provides accurate answers sourced from the internet and a user's personal knowledge base. It supports multiple AI models, search engines, and input formats including text, images, and local files. It can generate production-ready user interface pages from text or image inputs in seconds.
monocles.de is a search engine powered by the searx platform, offering features including store, mail, social chat, and translator functionality, with support for dark mode viewing. The service is developed by Arne-Brün Vogelsang, with copyright spanning 2020 to 2026, and runs on searx version 1.0.1.dev3+gfdb1f9be.d20220222.
Waltheri's go pattern search is a web application for searching go positions such as joseki and fuseki in a database of professional game records. Users create a position on a board and can find occurrences in pro games along with continuations played. It offers fuseki, joseki and manual search modes.
You.com provides web search APIs designed for AI and agentic applications. The APIs support web search, clean content extraction, and generation of grounded answers for large language models and AI agents, with custom query limits and free trial credits available.
An article by Andy Baio examining how AI companies use datasets and models from academic and nonprofit research groups. It describes Meta's Make-A-Video using Shutterstock clips and YouTube videos collected by Microsoft, and notes nonprofit datasets used for Stable Diffusion and other models. It argues this outsourcing shifts accountability and legal liability away from corporations.
Artificial Intelligence: A Modern Approach is the official companion site for the 4th US edition of the AI textbook of the same name, authored by Stuart Russell and Peter Norvig. The textbook is the most widely used AI textbook, adopted by over 1500 schools. The site provides supporting resources including the book's table of contents, code, course materials, exercises, figures, and errata.
AtomDB is an astrophysical plasma emission database providing atomic data for modeling X-ray spectra. It includes ionization and recombination rates, energy levels, wavelength and Einstein A values, electron and proton collision data, and density-sensitive line diagnostics for plasma modeling.
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.
automl-gs is a Python 3 AutoML module that takes an input CSV and a target field and generates a trained machine learning or deep learning model plus native Python code pipelines. It provides a zero code/model definition interface and performs random hyperparameter searches, reporting metrics for each trial in a CSV.
BreyerHorseRef is a collector reference site for Breyer model horses and animals, not affiliated with Breyer or Reeves International. Its database lists over 9,600 models with details such as size, mold, color and model number. Members can build in-search-of, private collection and horse showing lists, export PDF and CSV files, and list models for sale. Membership costs $35 a year.
CarNet.AI is a car make and model recognition API. The service reports recognizing the make, model and generation of most cars built since 1995. API access is obtained by messaging the service through its contact form. The company states it has data on 300 car brands and 3100+ models.
ch.at is a lightweight language model chat service accessible through HTTP, SSH, DNS, and an OpenAI-compatible API, plus a public agent board with posts, replies, feeds and search. It requires no JavaScript or tracking, and bots are welcome. State is held in RAM only, so a restart loses all data.
The Community Coordinated Modeling Center is a multi-agency partnership at NASA Goddard Space Flight Center that supports research and development for space science and space weather models. It provides free access to research models through an automated model run system, along with online visualization and analysis tools, model validation, forecasting support, and education resources.
A community project for exploring Earth's surface with community software. The site lists webinars, job postings, research groups and conference presentations, including the CSDMS 2026 conference on Modeling Landscapes in Motion at the University of Minnesota.
