Directory
Published directory entries matching your search.
Semantic Scholar is a free AI-powered research tool for scientific literature. It uses AI to understand the semantics of scientific literature to help scholars discover relevant research. It provides a developer API with paper search functionality, improved documentation and increased stability, and offers a beta Semantic Reader augmented reading tool for select papers.
Semantic Art Search is a search instance or metasearch resource for private web discovery.
Semantic Art Search is a search instance or metasearch resource for private web discovery.
arXiv Xplorer is a semantic search engine for arXiv. It supports open access interoperability with arXiv, bioRxiv and medRxiv, and is built using OpenAI's embeddings as a semantic search tool for these repositories.
Build semantic search and retrieval applications.
BabelNet is a multilingual encyclopedic dictionary and semantic network. It provides lexicographic and encyclopedic coverage of terms in 500 languages. The resource connects concepts and named entities in a large network of semantic relations, containing more than 20 million entries.
MediaWiki Code2Code Search is an AI-powered semantic neural retrieval tool for searching MediaWiki source code. It uses Sentence-Transformers to enable meaning-based search rather than keyword-only matching, allowing users to find functions, types, and templates across the entire MediaWiki ecosystem. It supports multiple programming languages including PHP, Python, JavaScript, Go, TypeScript and Lua, and provides sample evaluation queries for common code search tasks.
Meilisearch is a search engine that indexes content and exposes it through search, conversational interfaces and APIs. It supports full-text search, semantic search and hybrid search, and can be used on the managed Meilisearch Cloud or self-hosted as an open source engine. Official SDKs are available for several programming languages and frameworks.
Biblos is a tool for semantic search and multi-layered analysis of Biblical texts, using Chroma and instructor-large embeddings for retrieval. Search results are summarized with Anthropic's Claude, and the tool includes Greek New Testament text, Dodson Greek Lexicon definitions and Church Fathers' commentaries. The web UI is built with Streamlit.
LIVIVO is an interdisciplinary search engine for literature and information in the life sciences, run by ZB MED – Information Centre for Life Sciences. It searches library catalogues, publisher directories and databases such as PubMed, AGRICOLA and AGRIS through a standardised interface, using semantic search technology with controlled vocabularies. Results are sorted by relevance and can be narrowed with filters.
Searchthearxiv is a simple semantic search engine for machine learning papers on arXiv. Users can input arXiv links to find similar papers or use natural language queries to search for relevant research.
Graphlit is a context layer for AI agents. It provides real-time synchronization across services including Slack, GitHub, and Jira, operates via a single API with no operations overhead, and includes built-in semantic search.
Haystack is an open-source AI orchestration framework for building production-ready LLM applications in Python. It provides modular pipelines and agent workflows with explicit control over retrieval, routing, memory and generation, and is intended for RAG systems, multimodal applications, semantic search, question answering and autonomous agents. Installation is available via pip.
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.
SVGStud.io is an AI-powered SVG generator and editor. It generates SVGs from textual descriptions and optional example images, refines them iteratively, and offers semantic search across a library of 127303 SVGs plus a gallery and in-browser editing. Generated SVGs are licensed under CC-BY-SA 4.0. Inputs are logged and generated SVGs are added to the public library.
arthistoricum.net@heiDATA is a data publication repository hosted on Heidelberg University’s heiDATA platform, serving the Fachinformationsdienst Kunst – Fotografie – Design (art history, photography and design subject information service). It hosts datasets covering art, architecture and digital art history, including the DAH – International Journal for Digital Art History and projects focused on semantic data modeling for art and architecture.
DEMel is a semantically pre-structured, lemmatized database dedicated to Medieval Spanish. It is based on the digitized archive of the Diccionario del Español Medieval, discontinued at the end of 2007. Its sources include more than 600 literary and non-literary works or text and document collections, covering Spanish vocabulary from the 10th to the beginning of the 15th century. It provides pages for lemmas, attestations, bibliography, digitized archive and DEM volumes.
MeTA is a modern C++ data sciences toolkit. It provides text tokenization including deep semantic features like parse trees, inverted and forward indexes with compression and caching strategies, ranking functions for searching indexes, topic models, classification algorithms, graph algorithms, language models, a CRF implementation for POS-tagging and shallow parsing, and wrappers for liblinear and libsvm.
The ODISSEI Portal combines metadata from social sciences research data repositories into a single interface. It supports advanced semantic queries for findability and facilitates data access. A link to the Data Access Broker allows open datasets to be downloaded directly, while restricted access datasets link to the provider's page.
SIBiLS is a service of the Swiss Institute of Bioinformatics that provides personalized information retrieval in biological literature. It offers fully customizable searches in semantically enriched content using keywords or mapped biomedical entities from standardized and legacy vocabularies. Its collections include MEDLINE, PubMedCentral, Plazi treatments and PMC supplementary files, updated daily, and it is accessible via REST APIs.
StudyCraft is an open source, free study tool available for Windows, MacOS and Linux. It allows users to import study materials including PDFs, Markdown files, webpages and GitHub repositories, which are automatically indexed into a vector database for semantic search. Users can customize their imported content, and the tool automatically generates flashcard decks and practice tests, plus provides study session analytics to track progress. It supports self-hosted and cloud-hosted large language model integrations and is built for fast performance.
The Last Museum is a semantic search engine indexing public museum collections, allowing searches by theme, style, subject, or description. The site states it currently has around 6 million artworks indexed and is free to use, and that it is not affiliated with museums and does not own the images.
Vrite is an open-source, collaborative developer content platform for documentation, technical blogs, and knowledge bases. It includes a technical content editor with code editing, Markdown, and keyboard shortcuts, and can be self-hosted or used through a cloud service. It offers a headless API, JavaScript SDK, content variants, metadata, Git sync, and AI-powered semantic search. Paid plans begin with a 14-day free trial.
