Semantic Search Engines NLP Tools

Tools for building search systems that match semantic meaning and relevance using embeddings, neural networks, and dense/sparse retrieval methods. Does NOT include general information retrieval frameworks, traditional keyword-based search, or downstream NLP tasks like Q&A or summarization.

There are 56 semantic search engines tools tracked. 2 score above 50 (established tier). The highest-rated is smart-on-fhir/cumulus-etl at 60/100 with 22 stars and 813 monthly downloads.

Get all 56 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=nlp&subcategory=semantic-search-engines&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	smart-on-fhir/cumulus-etl Extract FHIR data, Transform with NLP and DEID tools, and then Load FHIR...	60	Established	22	Python
2	mirkosertic/FXDesktopSearch A JavaFX based desktop search application.	50	Established	181	Java
3	bent10/boox Search anything, instantly	47	Emerging	5	TypeScript
4	opensemanticsearch/open-semantic-search Open Source research tool to search, browse, analyze and explore large...	44	Emerging	1,154	Shell
5	opensemanticsearch/open-semantic-etl Python based Open Source ETL tools for file crawling, document processing...	42	Emerging	278	Python
6	opensemanticsearch/open-semantic-search-apps Python/Django based webapps and web user interfaces for search, structure...	39	Emerging	99	CSS
7	opensemanticsearch/open-semantic-entity-search-api Open Source REST API for named entity extraction, named entity linking,...	39	Emerging	200	Python
8	naver/splade SPLADE: sparse neural search (SIGIR21, SIGIR22)	38	Emerging	984	Python
9	hannawong/ColXLM Multilingual Retrieval on Yelp Search Engine ⚡	34	Emerging	80	Python
10	Leoglme/node-nlp-typescript nlp.js from axa-group in typescript 🚀. NLP library for building bots 🤖, with...	34	Emerging	24	TypeScript
11	AnthonySigogne/web-search-engine-ui UI - a simple web search engine	34	Emerging	32	HTML
12	yiming-liao/zhq 完全運行於客戶端的中文檢索引擎	33	Emerging	9	TypeScript
13	RugvedMavidipalli/Search-Engine Search Engine built using Java	32	Emerging	17	Java
14	RameshAditya/scoper Fuzzy and semantic search for captioned YouTube videos.	30	Emerging	268	Python
15	o19s/hello-nlp A natural language search microservice	30	Emerging	95	Python
16	metehan777/google-rerank-tool A Python cli-command tool for creating reports for any Google query.	28	Experimental	8	Python
17	lszoszk/UN-TreatyBodiesDocSearch Application enabling to search through the General Comments/ Recommendations...	26	Experimental	2	HTML
18	cabeywic/knowledge-base-search This project provides an efficient and scalable solution to search and query...	25	Experimental	4	Python
19	george-gca/ai_papers_search_tool Automatic paper clustering and search tool by fastext from Facebook Research	24	Experimental	2	Python
20	Yahia995/semantic-search-api NLP-powered semantic document search using HuggingFace transformers and FAISS	23	Experimental	5	Python
21	lakshaychhabra/MLSearchEngine This repo contains an NLP and ML based Search Engine for Stackoverflow Dataset.	22	Experimental	9	Jupyter Notebook
22	anonymous10112025-prog/GLiSE GLiSE: Grey Literature Search Engine	22	Experimental	—	Python
23	jpoehnelt/related-documents Find and rank text documents by similarity.	22	Experimental	4	TypeScript
24	mdipietro09/App_StringsMatcher String Matching Web App	21	Experimental	8	HTML
25	kmcleste/oracle-of-ammon CLI utility for creating Search APIs	21	Experimental	4	Python
26	jonahknip/o-drive-indexer Fast, AI-powered file search tool for shared drives. Index thousands of...	19	Experimental	—	Python
27	KvaytG/ru-wiki-search Smart search on Russian Wikipedia.	19	Experimental	—	Python
28	pradeep583/Search-It A lightweight web search engine built using BM25 for keyword relevance, BERT...	18	Experimental	3	Python
29	shreydan/youtube-in-video-search YouTube Question-Answering and Semantic Search.	17	Experimental	5	Python
30	czarinagluna/ml-powered-video-library Machine learning-powered video library that returns accurate results given...	16	Experimental	4	Jupyter Notebook
31	MohammadMoataz2/KnowledgeKapture KnowledgeKapture is an information retrieval system and search engine...	16	Experimental	3	Tcl
32	IvanKotik/Word-cloud-Search-engine-optimisation- Future project on search optimisation via NLP	16	Experimental	2	Jupyter Notebook
33	DevAsgari/ai-semantic-search-tool Python-based semantic search tool using pretrained Sentence-BERT for vector...	15	Experimental	—	Python
34	shruticreates01-ship-it/smart-search-ai AI-powered natural language product search (demo + PRD + metrics framework)	15	Experimental	1	—
35	ARUNAGIRINATHAN-K/Search-App A web-based search application for .txt files with five algorithms (Linear,...	15	Experimental	6	HTML
36	SonPari1/Search-Engine-Ui # Search Engine UI![Search Engine UI Cover](Assets/Image/Cover.jpg)**Search...	14	Experimental	—	CSS
37	Anaskaysar/SciRet-Scientific-Information-Made-Easy SciRet is a system that will retrieve authentic and informative data from a...	14	Experimental	1	Jupyter Notebook
38	thecloaq/cloaq-reranker gRPC service that reranks documents by relevance	14	Experimental	3	Python
39	altescy/tinysearch 🔍 Tiny python library for sparse/dense search	13	Experimental	7	Python
40	LLRHall/Astria Astria - Intelligent Search Engine for Lawyers and Common people	12	Experimental	13	JavaScript
41	Somespi/meliora meliora is a command-line tool for sorting files based on their content. that's it.	12	Experimental	3	Python
42	lyteabovenyte/Offline-Search Search the world you’ve saved, anytime, anywhere. (WAR EDITION)	12	Experimental	1	Rust
43	TelevisionNinja/search-engine This is a basic search engine I made for my information retrieval class.	11	Experimental	2	HTML
44	LexTOliver/web-scraping Search engine application and web scraping project to search specified...	11	Experimental	—	Python
45	SwapnilVerma209/mini_search An in-progress free and open source search engine.	11	Experimental	—	Python
46	nico916/best_search_engine- A "from-scratch" implementation of a search engine in Python. This project...	11	Experimental	—	Python
47	mahirp22/AI-Custom-Search-Engine 🔍 AI-powered custom search engine built with Flask and the Exa Search API.	11	Experimental	—	CSS
48	RRFLV/project-search Project Search is the code name for the search engine project in development...	11	Experimental	—	—
49	fccapria/scientify Modern platform for managing and sharing scientific publications 📚✨	11	Experimental	—	JavaScript
50	nsgowebjavaprog/Search-Engine https://search-engine-2fpyr9kd7hgwahsbtgoywb.streamlit.app/	11	Experimental	2	Python
51	frans-johansson/code-query Information retrieval on source code through natural language queries	10	Experimental	1	Python
52	deepindexer/deepi-wp WordPress Plugin for Deepi Search. Upgrade your site's "lexical search" to...	10	Experimental	1	PHP
53	vicol13/search-engine Inverted index search engine with lemmatized keys and weighted(corpus based)...	10	Experimental	1	Kotlin
54	ElfarraDev/NimbleSearch NimbleSearch is a lightweight, efficient search index solution for small to...	10	Experimental	1	Python
55	HarisAli-git/Search-Engine-using-NLP-with-Doc-Similarity-index A search engine with Doc-Doc similarity incidence matrix to show the...	10	Experimental	1	Jupyter Notebook
56	tsureshkumar/semdesk Semantic Desktop Search - search for answers not the file names	10	Experimental	1	Rust