Vector DB From Scratch Vector Databases

Educational and minimalist vector database implementations built to understand core concepts and internals. Includes toy/learning projects, lightweight engines, and pure-Python implementations prioritizing clarity over production features. Does NOT include enterprise databases, managed services, or specialized implementations (embedded SQLite variants, REST API wrappers, or domain-specific systems like NFT databases).

There are 174 vector db from scratch tools tracked. 2 score above 70 (verified tier). The highest-rated is MariaDB/server at 73/100 with 7,297 stars. 4 of the top 10 are actively maintained.

Get all 174 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=vector-db&subcategory=vector-db-from-scratch&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	MariaDB/server MariaDB server is a community developed fork of MySQL server. Started by...	73	Verified	7,297	C++
2	AlayaDB-AI/AlayaLite AlayaLite – A Fast, Flexible Vector Database for Everyone.	70	Verified	199	C++
3	infiniflow/infinity The AI-native database built for LLM applications, providing incredibly fast...	66	Established	4,437	C++
4	nnethercott/hannoy Production-ready KV-backed HNSW implementation in Rust using LMDB	66	Established	71	Rust
5	dingodb/dingo A multi-modal vector database that supports upserts and vector queries using...	62	Established	1,698	Java
6	oceanbase/seekdb The AI-Native Search Database. Unifies vector, text, structured and...	62	Established	2,451	C++
7	zilliztech/knowhere Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.	61	Established	328	C++
8	dingodb/dingo-store A distributed Key-Value Storage using Raft	59	Established	161	C++
9	datawhalechina/easy-vecdb 📚 从零开始的向量数据库原理与实践教程，在线阅读地址：https://easy-vecdb.datawhale.cc/	56	Established	226	Jupyter Notebook
10	endee-io/endee Endee.io – A high-performance vector database, designed to handle up to 1B...	56	Established	308	C++
11	VectorDB-NTU/RaBitQ-Library A lightweight library for the RaBitQ algorithm and its applications in vector search.	56	Established	129	C++
12	thustorage/PipeANN A low-latency, billion-scale, and updatable graph-based vector store on SSD.	55	Established	102	Jupyter Notebook
13	gusye1234/nano-vectordb A simple, easy-to-hack Vector Database	53	Established	190	Python
14	schwabauerbriantomas-gif/m2m-vector-search Edge Vector search engine with Vulkan GPU acceleration, hierarchical...	53	Established	24	Python
15	jina-ai/vectordb A Python vector database you just need - no more, no less.	51	Established	644	Python
16	muxi-ai/faissx High-performance remote FAISS server for vector similarity search, with full...	49	Emerging	4	Python
17	MinishLab/vicinity Lightweight Nearest Neighbors with Flexible Backends	49	Emerging	334	Python
18	vortezwohl/Bhakti An easy-to-use vector database.	49	Emerging	37	Python
19	varshith-Git/valori A high-performance vector database library for Python that provides...	48	Emerging	19	Python
20	Veeresh-Hanni/DBDuck Universal Data Object Model in Pytghon for SQL, Nosql, Graph, Vector DBMS	47	Emerging	2	Python
21	nickna/Neighborly An open-source vector database	47	Emerging	21	C#
22	pomagrenate/pomaidb PomaiDB Vector Database for low performance devices	47	Emerging	15	C++
23	BBC-Esq/VectorDB-Plugin Program that lets you ask questions about your documents including audio and...	46	Emerging	362	Python
24	rapidsai/cuvs-lucene A Lucene codec for vector search and clustering on the GPU	46	Emerging	7	Java
25	ejaasaari/lorann Approximate Nearest Neighbor search using reduced-rank regression, with...	46	Emerging	51	C++
26	syalia-srl/beaver All-in-one, pure-python, embedded database for relational data, documents,...	45	Emerging	35	Python
27	epsilla-cloud/vectordb Epsilla is a high performance Vector Database Management System	45	Emerging	871	C++
28	VectorDB-NTU/Extended-RaBitQ [SIGMOD 2025] Practical and Asymptotically Optimal Quantization of...	44	Emerging	62	C++
29	cgtuebingen/ggnn GGNN: State of the Art Graph-based GPU Nearest Neighbor Search	44	Emerging	170	Cuda
30	1yefuwang1/vectorlite Fast, SQL powered, in-process vector search for any language with an SQLite driver	44	Emerging	351	C++
31	Dripfarm/SVDB Swift Vector Database. On-device, local vector database for building the...	42	Emerging	219	Swift
32	vitrivr/cottontaildb Cottontail DB is a column store vector database aimed at multimedia...	42	Emerging	40	Kotlin
33	ShravanSunder/hnswlib-wasm hnswlib-wasm attempts to create a browser friendly version of hnswlib	42	Emerging	64	C++
34	AutoCookies/pomaidb PomaiDB Vector Database for low performance devices	41	Emerging	15	C++
35	MenxLi/tiny_vectordb A small and fast Python JIT vector database	40	Emerging	2	Python
36	mmilunovic/m2vdb vector db built by someone with no idea how to build a vector db	40	Emerging	8	Python
37	BirchKwok/lynsedb A pure Python-implemented, lightweight, server-optional, multi-end...	40	Emerging	39	Python
38	sauravniraula/fastembed-vectorstore In-memory vector store with FastEmbed integration for Python applications.	40	Emerging	2	Python
39	vinerya/faiss_vector_aggregator This Python library provides a suite of advanced methods for aggregating...	39	Emerging	2	Python
40	0xDebabrata/citrus (distributed) vector database	39	Emerging	105	Python
41	makr-code/ThemisDB Themis Database System - High-performance C++ hybrid-database...	38	Emerging	4	C++
42	feather-store/feather Embedded vector database + living context engine Part of Hawky.ai —...	38	Emerging	3	C++
43	MChatzakis/DARTH [SIGMOD 2026] DARTH: Declarative Recall Through Early Termination for...	37	Emerging	23	C++
44	ZeusDB/zeusdb High-performance database management system	37	Emerging	9	Python
45	tylerpuig/tinyvec TinyVecDB is an ultra fast embedded vector database.	37	Emerging	52	C
46	krishcdbry/nexadb NexaDB - A lightweight NoSQL database with vector search, TOON format, and...	37	Emerging	7	Python
47	firstbatchxyz/hollowdb-vector A decentralized vector database for building vector search applications	34	Emerging	99	TypeScript
48	wibyuan/easyANN This project implements 30+ variants of ANN algorithms to find the K nearest...	34	Emerging	12	C++
49	lynnlangit/learning-nosql Companion repository to Linked In Learning course 'Cloud NoSQL for SQL Pros'	34	Emerging	5	—
50	prrao87/db-hub-fastapi Async bulk data ingestion and querying in various document, graph and vector...	33	Emerging	40	Python
51	mihirahuja1/vectorwrap Universal vector search wrapper for Postgres, MySQL, SQLite (pgvector,...	33	Emerging	44	Python
52	JadenGeller/similarity-topology Efficient nearest neighbor search in Swift	33	Emerging	8	Swift
53	EmbedInAI/EmbedInDB A vector database that empowers AI with persistent memory	33	Emerging	7	Python
54	antarys-ai/python Python client for Antarys vector database, optimized for large-scale vector...	32	Emerging	236	Python
55	knowusuboaky/VectrixDB Where vectors come alive - A lightweight, visual-first vector database with...	32	Emerging	2	Python
56	ashvardanian/JaccardIndex Optimizing bit-level Jaccard Index and Population Counts for large-scale...	32	Emerging	21	Python
57	ToucanDB/ToucanDB ToucanDB is a brand-new micro ML-first database engine 🦜	32	Emerging	13	Python
58	sarabesh/PuppyDB This is an experimental learning project to explore how vector databases...	32	Emerging	4	Python
59	atasoglu/sqlite-vec-client A lightweight Python client around sqlite-vec for CRUD and similarity search.	31	Emerging	1	Python
60	mantzaris/LMDiskANN.jl Julia Implementation of Low Memory Disk ANN (LM-DiskANN)	31	Emerging	7	Julia
61	skyzh/write-you-a-vector-db A Vector Database Tutorial (over CMU-DB's BusTub system)	30	Emerging	756	C++
62	maurocanuto/mempack MemPack is a blazing-fast, lightweight alternative to heavy vector...	30	Emerging	9	Python
63	vital-ai/vital-vitalsigns-python Knowledge Model Runtime, Ontology management, and interface to Graph and...	30	Emerging	5	Python
64	ericmillsio/whiplash Serverless, lightweight, and fast vector database on top of DynamoDB	30	Emerging	25	Python
65	ksm26/vector-databases-embeddings-applications Unlock the power of vector databases with the "Vector Databases: from...	29	Experimental	5	Jupyter Notebook
66	rizquuula/pyvectordb Python wrapper for many Vector Databases	29	Experimental	3	Python
67	thewebscraping/crossvector Production-ready Python vector database library with unified API for...	29	Experimental	1	Python
68	ehsanghaffar/vector-store-api This project aims to provide an efficient and scalable API for embedding and...	28	Experimental	10	Python
69	starkdg/hftrie index binary vectors for efficient nearest neighbor search	28	Experimental	10	C++
70	vortezwohl/Dipamkara A light-weight vector database engine.	28	Experimental	2	Python
71	QDL123/Periplus A remote cache for vector databases which allows for a dynamically updated...	28	Experimental	8	C++
72	JaneaSystems/jecq Faiss-based library for efficient similarity search	28	Experimental	57	C++
73	rajathshttgr/zoro-db A Vector Search Engine Built from Scratch in C++	27	Experimental	6	C++
74	replikativ/proximum Versioned, fast and scalable nearest neighbor search.	27	Experimental	20	Clojure
75	krejciad/kramdb Simple in-RAM database system	27	Experimental	2	C++
76	jmelovich/VectorDatabasePluginUE A vector 'database' plugin for Unreal Engine 5. Built for leveraging the...	27	Experimental	7	C++
77	gifton/VectorCore CPU-bound vector math library with SIMD optimization, distance metrics, and...	26	Experimental	1	Swift
78	torinriley/VecStream Efficient, scalable, and lightweight vector database	26	Experimental	1	Python
79	oneKn8/VectorVault HNSW approximate nearest neighbor engine from scratch in C++20. AVX2...	26	Experimental	1	C++
80	vectordbpipe/vectorDBpipe A modular text embedding and vector database pipeline for local and cloud...	26	Experimental	1	Python
81	VQLite/VQLite VQLite - Simple and Lightweight Vector Search Engine based on Google ScaNN	26	Experimental	92	Go
82	tsvet01/quiverdb Embeddable vector database for edge AI. Lightning-fast semantic search that...	26	Experimental	3	C++
83	mingyu-hkustgz/Res-Infer Distance Computaion for Vector Databases	26	Experimental	12	C++
84	doganarif/vectordb In-memory vector database with pluggable indexing algorithms, metadata...	26	Experimental	11	Python
85	oscarcitoz/vector-db A FastAPI-based API for managing vector database operations like creating...	25	Experimental	1	Python
86	NDXDeveloper/formation-mariadb 🐬 Formation complète MariaDB 11.8 LTS en français . SQL, HA, DevOps,...	25	Experimental	18	—
87	nhevers/vecstore lightweight vector store with HNSW indexing	25	Experimental	6	Python
88	maylad31/vector_sqlite Faiss with sqlite	25	Experimental	5	Python
89	capybara-brain346/capybaradb capybaradb - a toy Vector DB implementation from scratch in Python. Explore...	24	Experimental	3	Python
90	atisharma/fvdb Thin porcelain around the FAISS vector database.	24	Experimental	2	Hy
91	PranavBhatP/velox-db An hobby project to construct a fully functioning vector database from...	24	Experimental	1	C++
92	JGalego/VektorDB A minimal vector database for educational purposes.	23	Experimental	3	Python
93	mingyu-hkustgz/RESQ High-Ratio Vector Quantization	23	Experimental	10	C++
94	haja-k/mysql-to-pgvector-embeddings vectorizing data from mysql database to vector so it can be used by LLM in...	23	Experimental	2	Python
95	MukundaKatta/thoth Thoth — Embedded Vector Database. Embedded vector database (SQLite for vectors)	22	Experimental	—	Python
96	gsavla6-hue/java-vector-database High-performance Java vector database implementation with HNSW indexing,...	22	Experimental	—	Java
97	lexxai/django-mariadb-vector-demo A minimal demo project showing how to build article recommendations using...	22	Experimental	—	Python
98	deathbeam/vectorspace Directory file watcher for automatically creating and querying vector embeddings.	21	Experimental	4	Python
99	kroq86/mcp_vector_db VectorDB MCP server	21	Experimental	—	Python
100	LongmaoTeamTf/ant Open-source vector database built to embedding similarity search	21	Experimental	10	Python
101	ribagolx10/crossvector 🔗 Simplify vector database operations with CrossVector, a unified Python...	21	Experimental	—	Python
102	bosekarmegam/vecforge VecForge is a universal, local-first Python vector database with enterprise...	21	Experimental	—	Python
103	N2FlowJS/nbase NBase is a high-performance vector database for efficient similarity search,...	21	Experimental	2	TypeScript
104	Icingworld/dreamdb 轻量级向量数据库	21	Experimental	—	C++
105	jerryli99/jerry_vectorDB A lightweight vector database	21	Experimental	—	C++
106	shlokkvaishnav/nano-db Persistent Vector Search Engine built from scratch featuring disk-based HNSW...	21	Experimental	—	C++
107	UnrealJon/DTDR Transform-domain representation enabling 3–4× storage reduction with direct...	21	Experimental	—	Jupyter Notebook
108	NachoBrito/vulcano An in-process, lightweight vector database written in modern Java	21	Experimental	—	Java
109	jwill9999/Vector-DB-Service A microservice that allows upload of documents from google services, and...	21	Experimental	—	TypeScript
110	leitoooatr/PythonVectorDB 🗄️ Manage and search large vector datasets efficiently with this pure Python...	21	Experimental	—	Python
111	britorbs/consciousdb 🗄️ Streamline data analysis with ConsciousDB, a vector database that...	21	Experimental	—	Python
112	AlexHaborets/vectordb A minimalistic, pure-Python vector database for semantic search and RAG...	21	Experimental	—	Python
113	amhoba/vector-search-db A high-performance, persistent vector search engine written in C++17 with...	21	Experimental	—	C++
114	cmessin02-cmyk/Sentry-Vector-The-AI-Powered-Immutable-Ledger A high-performance, C++ based Vector Database with HMAC-SHA256 blockchain...	20	Experimental	1	C++
115	starkdg/mvptree multiple vantage point distance-based tree data structure	20	Experimental	8	C++
116	gtfintechlab/Universal-NFT-Vector-Database The Universal NFT Vector Database: A Scalable Vector Database for NFT...	20	Experimental	7	Jupyter Notebook
117	lcj2021/mini-ivf A cute toy of IVF (PQ).	20	Experimental	5	C++
118	ocramz/vectordb Simple vector database based on annoy and sqlite3	19	Experimental	3	Python
119	danilop/knn-search-algorithm-comparison KNN Search Algorithm Comparison – This project compares the performance of...	19	Experimental	4	Python
120	RKirlew/SoraDB-A-Lightweight-Vector-Database SoraDB is a custom-built vector storage engine designed to manage and query...	19	Experimental	1	C++
121	thkbit-labs/vecmodel A model-based, ORM-inspired abstraction for vector databases.	19	Experimental	2	Makefile
122	colbertdb/colbertdb Open source ColBERT based document database	19	Experimental	3	Python
123	yusupwinata/Basic-VectorDB Build vector database using LangChain, Hugging Face, Chroma and FAISS.	19	Experimental	2	Jupyter Notebook
124	AWeirdDev/vdb37 A simple vector database.	18	Experimental	1	Python
125	NautilusDB-cloud/nautilusdb-cli The simple client of NautilusDB, a Clound-Native Vector Search Service	18	Experimental	2	Python
126	Flagro/VecMetaQ Server over Python Faiss serverless implementation to match interfaces used...	18	Experimental	2	Python
127	B-R-P/VStore Embedded key-value store with vector similarity search	18	Experimental	1	Python
128	nathangtg/dbms-research This is the repository for ZGQ (Zone Graph Quantization)m Which is now...	18	Experimental	1	Python
129	Scintirete/Scintirete Scintirete 是一款基于 HNSW 算法实现的、嵌入式友好的、面向生产的向量数据库。Scintirete is a lightweight,...	18	Experimental	1	Go
130	jballo/vector-db-engine A FastAPI service that lets users create, read, update, and delete document...	18	Experimental	1	Python
131	Maverick0351a/consciousdb ConsciousDB – Your Vector Database Is the Model	18	Experimental	1	Python
132	timothyckl/iota a minimal local embedding database.	18	Experimental	2	Python
133	SherifSystems/PythonVectorDB Pure Python vector database • int8 quantized • ~1100 QPS @ 50k vectors •...	17	Experimental	—	Python
134	hritik2002/local-vectordb Local vector database with embeddings & semantic search. Uses HNSW for fast...	17	Experimental	—	—
135	Md-Emon-Hasan/Vector-Database Designed to store and retrieve high-dimensional data, such as embeddings,...	17	Experimental	1	Jupyter Notebook
136	kanitakadusic/bsc-thesis Vector Databases: Use Cases, Algorithms and Key Features	17	Experimental	—	TeX
137	gifton/VectorAccelerate Swift6 GPU-accelerated vector operations using Metal4 shaders for Apple...	17	Experimental	2	Swift
138	matthewwangg/vector-database A performant in-memory vector database with an HNSW index, data persistence,...	17	Experimental	—	C++
139	mingyu-hkustgz/LabelANN Label Filtering Vector Similarity Search	17	Experimental	4	C++
140	yezz123/vectorai A Vector Database REST API with custom indexing algorithms	16	Experimental	4	Python
141	plkumar/simple-vectordb-cpp Experimental HNSW Index implementation.	16	Experimental	2	JavaScript
142	takurot/Pyrope Pyrope is a high-performance, adaptive Vector Database built as an extension...	15	Experimental	—	C#
143	JohnnyHyytiainen/glossary_db Personal Glossary Database to help keep track on terms and theory for school...	15	Experimental	2	Python
144	nileshkhetrapal/YassQueenDB Graph database library that allows you to store, analyze, and search through...	14	Experimental	16	Python
145	gifton/VectorIndex CPU-bound vector indexing library supporting HNSW and IVF algorithms for...	14	Experimental	1	Swift
146	rosaia/vecworks Seamlessly manage vectorized data in Python	14	Experimental	1	Python
147	tweedge/vectordb-docker-base Python 3.10-slim with VectorDB (vectordb2==0.1.9) and certain models...	13	Experimental	—	Dockerfile
148	RasaiStewart/Vector-database-using-vectordb My attempt to create a vector database to store the names of books I have...	13	Experimental	—	Python
149	tanushachoudhary/VectorDB A production-ready vector database system that stores document embeddings...	13	Experimental	—	Python
150	1226085293/MiniVectorDB Lightweight, self-hosted Node.js vector database using WASM-based HNSW with...	13	Experimental	—	TypeScript
151	BBC-Esq/VectorDB-Plugin-for-KoboldAI Basic vector database plugin that works wth KoboldAI. Adds documents,...	13	Experimental	4	Python
152	yichunzhao/python-learning Taking it slow and easy—Python, here I come. 🐍✨	13	Experimental	—	Python
153	TekilaSS/Educational-Vector-Database 📚 Learn to build and understand Vector Databases step-by-step in Arabic,...	13	Experimental	—	Python
154	Ronakagrwal000/vector-cache-optimizer ⚡ Optimize vector searches with a hyper-efficient cache that uses machine...	13	Experimental	—	Python
155	VuBacktracking/bert-faiss-qa-system Q&A System using BERT and Faiss Vector Database	13	Experimental	11	Python
156	patw/InstructorVec Create dense vectors using the instructor-large model, running on CPU in...	13	Experimental	—	Python
157	waynewbishop/quiver Quiver is a Swift package that provides vector mathematics, numerical...	13	Experimental	—	Swift
158	natenberenstein/deep-dive-databases Knowledge base covering database internals -- storage engines, data models,...	13	Experimental	—	—
159	RijoSLal/build-your-own-vectordb This repository is a fun weekend project that builds a lightweight vector...	12	Experimental	1	Python
160	jsramesh1990/storing-and-fetching-date-indexed-data Static vs dynamic containers, fixed vs resizable storage, date-indexed data...	12	Experimental	1	C++
161	PluginsKers/SemanDoc A lightweight, out-of-the-box semantic vector knowledge base management system.	11	Experimental	1	Python
162	ryzhakar/async-annoy Asynchronous wrapper around the Annoy library for approximate nearest...	11	Experimental	—	Python
163	handisaputra/astra-db-ts The free bug distribution of the @datastax/astra-db-ts version 1.5.0	11	Experimental	—	—
164	kisasexypantera94/urukrama Simple and Efficient DiskANN implementation	11	Experimental	—	C++
165	s-emanuilov/vector_forge Vector Forge is a Python package designed for easy transformation of various...	11	Experimental	—	Python
166	noNScop/Vector_DB This project is a simple and efficient tool for creating and querying a...	11	Experimental	—	Python
167	amhsirak/vectin Vector store for text embedding & similarity search	11	Experimental	3	Python
168	StealthyPanda/astraldb Yet another fast and lightweight vector database.	11	Experimental	—	Python
169	Ate329/VDBpy A simple python vector database allows difference search methods (consine...	11	Experimental	—	Python
170	bariscamli/Vector-Search-with-FAISS Vector search using embeddings, FAISS and Product Quantization with custom...	11	Experimental	—	Python
171	nodestark/knn-esp32-vector Tiny ESP32 KNN Vector Database	10	Experimental	1	C
172	ekorman/affine A unified interface for vector databases	10	Experimental	2	Python
173	KevKibe/memvectordb-python-sdk memvectorDB python SDK.	10	Experimental	2	Python
174	swastikmaiti/Vector_Database Implementing Vector Database on CoNaLa dataset to retrieve program snippets...	10	Experimental	2	Jupyter Notebook

Comparisons in this category

nano-vectordb and vectordb (53 vs 51)