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 157 vector db from scratch tools tracked. 1 score above 70 (verified tier). The highest-rated is MariaDB/server at 76/100 with 7,297 stars. 4 of the top 10 are actively maintained.

Get all 157 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...	76	Verified	7,297	C++
2	infiniflow/infinity The AI-native database built for LLM applications, providing incredibly fast...	69	Established	4,437	C++
3	AlayaDB-AI/AlayaLite AlayaLite – A Fast, Flexible Vector Database for Everyone.	66	Established	199	C++
4	oceanbase/seekdb The AI-Native Search Database. Unifies vector, text, structured and...	61	Established	2,451	C++
5	schwabauerbriantomas-gif/m2m-vector-search Edge Vector search engine with Vulkan GPU acceleration, hierarchical...	61	Established	24	Python
6	gusye1234/nano-vectordb A simple, easy-to-hack Vector Database	60	Established	190	Python
7	nnethercott/hannoy Production-ready KV-backed HNSW implementation in Rust using LMDB	60	Established	71	Rust
8	dingodb/dingo A multi-modal vector database that supports upserts and vector queries using...	58	Established	1,698	Java
9	endee-io/endee Endee.io – A high-performance vector database, designed to handle up to 1B...	57	Established	308	C++
10	zilliztech/knowhere Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.	57	Established	328	C++
11	dingodb/dingo-store A distributed Key-Value Storage using Raft	55	Established	161	C++
12	MinishLab/vicinity Lightweight Nearest Neighbors with Flexible Backends	52	Established	334	Python
13	muxi-ai/faissx High-performance remote FAISS server for vector similarity search, with full...	50	Established	4	Python
14	jina-ai/vectordb A Python vector database you just need - no more, no less.	50	Established	644	Python
15	VectorDB-NTU/RaBitQ-Library A lightweight library for the RaBitQ algorithm and its applications in vector search.	50	Established	129	C++
16	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/	50	Established	226	Jupyter Notebook
17	thustorage/PipeANN A low-latency, billion-scale, and updatable graph-based vector store on SSD.	49	Emerging	102	Jupyter Notebook
18	varshith-Git/valori A high-performance vector database library for Python that provides...	46	Emerging	19	Python
19	Veeresh-Hanni/DBDuck Universal Data Object Model in Pytghon for SQL, Nosql, Graph, Vector DBMS	45	Emerging	2	Python
20	vortezwohl/Bhakti An easy-to-use vector database.	45	Emerging	37	Python
21	rapidsai/cuvs-lucene A Lucene codec for vector search and clustering on the GPU	43	Emerging	7	Java
22	pomagrenate/pomaidb PomaiDB Vector Database for low performance devices	43	Emerging	15	C++
23	ejaasaari/lorann Approximate Nearest Neighbor search using reduced-rank regression, with...	43	Emerging	51	C++
24	AutoCookies/pomaidb PomaiDB Vector Database for low performance devices	42	Emerging	15	C++
25	nickna/Neighborly An open-source vector database	40	Emerging	21	C#
26	BBC-Esq/VectorDB-Plugin Program that lets you ask questions about your documents including audio and...	39	Emerging	362	Python
27	syalia-srl/beaver All-in-one, pure-python, embedded database for relational data, documents,...	39	Emerging	35	Python
28	vinerya/faiss_vector_aggregator This Python library provides a suite of advanced methods for aggregating...	38	Emerging	2	Python
29	epsilla-cloud/vectordb Epsilla is a high performance Vector Database Management System	38	Emerging	871	C++
30	VectorDB-NTU/Extended-RaBitQ [SIGMOD 2025] Practical and Asymptotically Optimal Quantization of...	37	Emerging	62	C++
31	ZeusDB/zeusdb High-performance database management system	37	Emerging	9	Python
32	makr-code/ThemisDB Themis Database System - High-performance C++ hybrid-database...	37	Emerging	4	C++
33	cgtuebingen/ggnn GGNN: State of the Art Graph-based GPU Nearest Neighbor Search	37	Emerging	170	Cuda
34	feather-store/feather Embedded vector database + living context engine Part of Hawky.ai —...	37	Emerging	3	C++
35	1yefuwang1/vectorlite Fast, SQL powered, in-process vector search for any language with an SQLite driver	37	Emerging	351	C++
36	knowusuboaky/VectrixDB Where vectors come alive - A lightweight, visual-first vector database with...	36	Emerging	2	Python
37	vitrivr/cottontaildb Cottontail DB is a column store vector database aimed at multimedia...	35	Emerging	40	Kotlin
38	ShravanSunder/hnswlib-wasm hnswlib-wasm attempts to create a browser friendly version of hnswlib	35	Emerging	64	C++
39	Dripfarm/SVDB Swift Vector Database. On-device, local vector database for building the...	35	Emerging	219	Swift
40	sauravniraula/fastembed-vectorstore In-memory vector store with FastEmbed integration for Python applications.	34	Emerging	2	Python
41	mmilunovic/m2vdb vector db built by someone with no idea how to build a vector db	33	Emerging	8	Python
42	MenxLi/tiny_vectordb A small and fast Python JIT vector database	33	Emerging	2	Python
43	BirchKwok/lynsedb A pure Python-implemented, lightweight, server-optional, multi-end...	33	Emerging	39	Python
44	krishcdbry/nexadb NexaDB - A lightweight NoSQL database with vector search, TOON format, and...	33	Emerging	7	Python
45	0xDebabrata/citrus (distributed) vector database	32	Emerging	105	Python
46	MChatzakis/DARTH [SIGMOD 2026] DARTH: Declarative Recall Through Early Termination for...	31	Emerging	23	C++
47	wibyuan/easyANN This project implements 30+ variants of ANN algorithms to find the K nearest...	30	Emerging	12	C++
48	atasoglu/sqlite-vec-client A lightweight Python client around sqlite-vec for CRUD and similarity search.	30	Emerging	1	Python
49	tylerpuig/tinyvec TinyVecDB is an ultra fast embedded vector database.	30	Emerging	52	C
50	replikativ/proximum Versioned, fast and scalable nearest neighbor search.	28	Experimental	20	Clojure
51	thewebscraping/crossvector Production-ready Python vector database library with unified API for...	28	Experimental	1	Python
52	lynnlangit/learning-nosql Companion repository to Linked In Learning course 'Cloud NoSQL for SQL Pros'	27	Experimental	5	—
53	firstbatchxyz/hollowdb-vector A decentralized vector database for building vector search applications	27	Experimental	99	TypeScript
54	mihirahuja1/vectorwrap Universal vector search wrapper for Postgres, MySQL, SQLite (pgvector,...	27	Experimental	44	Python
55	sarabesh/PuppyDB This is an experimental learning project to explore how vector databases...	26	Experimental	4	Python
56	prrao87/db-hub-fastapi Async bulk data ingestion and querying in various document, graph and vector...	26	Experimental	40	Python
57	ToucanDB/ToucanDB ToucanDB is a brand-new micro ML-first database engine 🦜	26	Experimental	13	Python
58	antarys-ai/python Python client for Antarys vector database, optimized for large-scale vector...	26	Experimental	236	Python
59	JadenGeller/similarity-topology Efficient nearest neighbor search in Swift	26	Experimental	8	Swift
60	EmbedInAI/EmbedInDB A vector database that empowers AI with persistent memory	26	Experimental	7	Python
61	ashvardanian/JaccardIndex Optimizing bit-level Jaccard Index and Population Counts for large-scale...	25	Experimental	21	Python
62	mantzaris/LMDiskANN.jl Julia Implementation of Low Memory Disk ANN (LM-DiskANN)	24	Experimental	7	Julia
63	maurocanuto/mempack MemPack is a blazing-fast, lightweight alternative to heavy vector...	24	Experimental	9	Python
64	klu-ai/EmbedKit Swift library extending MLX Embed	24	Experimental	2	Swift
65	vortezwohl/Dipamkara A light-weight vector database engine.	24	Experimental	2	Python
66	skyzh/write-you-a-vector-db A Vector Database Tutorial (over CMU-DB's BusTub system)	23	Experimental	756	C++
67	rajathshttgr/zoro-db A Vector Search Engine Built from Scratch in C++	23	Experimental	6	C++
68	vital-ai/vital-vitalsigns-python Knowledge Model Runtime, Ontology management, and interface to Graph and...	23	Experimental	5	Python
69	nhevers/vecstore lightweight vector store with HNSW indexing	23	Experimental	6	Python
70	ericmillsio/whiplash Serverless, lightweight, and fast vector database on top of DynamoDB	23	Experimental	25	Python
71	torinriley/VecStream Efficient, scalable, and lightweight vector database	23	Experimental	1	Python
72	NachoBrito/vulcano An in-process, lightweight vector database written in modern Java	22	Experimental	—	Java
73	UnrealJon/DTDR Transform-domain representation enabling 3–4× storage reduction with direct...	22	Experimental	—	Jupyter Notebook
74	MukundaKatta/thoth Thoth — Embedded Vector Database. Embedded vector database (SQLite for vectors)	22	Experimental	—	Python
75	gsavla6-hue/java-vector-database High-performance Java vector database implementation with HNSW indexing,...	22	Experimental	—	Java
76	lexxai/django-mariadb-vector-demo A minimal demo project showing how to build article recommendations using...	22	Experimental	—	Python
77	leitoooatr/PythonVectorDB 🗄️ Manage and search large vector datasets efficiently with this pure Python...	22	Experimental	—	Python
78	britorbs/consciousdb 🗄️ Streamline data analysis with ConsciousDB, a vector database that...	22	Experimental	—	Python
79	ribagolx10/crossvector 🔗 Simplify vector database operations with CrossVector, a unified Python...	22	Experimental	—	Python
80	bosekarmegam/vecforge VecForge is a universal, local-first Python vector database with enterprise...	22	Experimental	—	Python
81	kroq86/mcp_vector_db VectorDB MCP server	22	Experimental	—	Python
82	rizquuula/pyvectordb Python wrapper for many Vector Databases	22	Experimental	3	Python
83	JaneaSystems/jecq Faiss-based library for efficient similarity search	22	Experimental	57	C++
84	ksm26/vector-databases-embeddings-applications Unlock the power of vector databases with the "Vector Databases: from...	22	Experimental	5	Jupyter Notebook
85	tsvet01/quiverdb Embeddable vector database for edge AI. Lightning-fast semantic search that...	22	Experimental	3	C++
86	NDXDeveloper/formation-mariadb 🐬 Formation complète MariaDB 11.8 LTS en français . SQL, HA, DevOps,...	21	Experimental	18	—
87	QDL123/Periplus A remote cache for vector databases which allows for a dynamically updated...	21	Experimental	8	C++
88	starkdg/hftrie index binary vectors for efficient nearest neighbor search	21	Experimental	10	C++
89	ehsanghaffar/vector-store-api This project aims to provide an efficient and scalable API for embedding and...	21	Experimental	10	Python
90	krejciad/kramdb Simple in-RAM database system	21	Experimental	2	C++
91	oneKn8/VectorVault HNSW approximate nearest neighbor engine from scratch in C++20. AVX2...	20	Experimental	1	C++
92	jmelovich/VectorDatabasePluginUE A vector 'database' plugin for Unreal Engine 5. Built for leveraging the...	20	Experimental	7	C++
93	gifton/VectorCore CPU-bound vector math library with SIMD optimization, distance metrics, and...	20	Experimental	1	Swift
94	PranavBhatP/velox-db An hobby project to construct a fully functioning vector database from...	20	Experimental	1	C++
95	doganarif/vectordb In-memory vector database with pluggable indexing algorithms, metadata...	20	Experimental	11	Python
96	vectordbpipe/vectorDBpipe A modular text embedding and vector database pipeline for local and cloud...	20	Experimental	1	Python
97	maticly/LabHub OLTP to OLAP ETL + Semantic Search Engine	19	Experimental	—	Python
98	jwill9999/Vector-DB-Service A microservice that allows upload of documents from google services, and...	19	Experimental	—	TypeScript
99	jerryli99/jerry_vectorDB A lightweight vector database	19	Experimental	—	C++
100	amhoba/vector-search-db A high-performance, persistent vector search engine written in C++17 with...	19	Experimental	—	C++
101	Icingworld/dreamdb 轻量级向量数据库	19	Experimental	—	C++
102	shlokkvaishnav/nano-db Persistent Vector Search Engine built from scratch featuring disk-based HNSW...	19	Experimental	—	C++
103	mingyu-hkustgz/Res-Infer Distance Computaion for Vector Databases	19	Experimental	12	C++
104	VQLite/VQLite VQLite - Simple and Lightweight Vector Search Engine based on Google ScaNN	19	Experimental	92	Go
105	AlexHaborets/vectordb A minimalistic, pure-Python vector database for semantic search and RAG...	19	Experimental	—	Python
106	maylad31/vector_sqlite Faiss with sqlite	18	Experimental	5	Python
107	capybara-brain346/capybaradb capybaradb - a toy Vector DB implementation from scratch in Python. Explore...	18	Experimental	3	Python
108	oscarcitoz/vector-db A FastAPI-based API for managing vector database operations like creating...	18	Experimental	1	Python
109	atisharma/fvdb Thin porcelain around the FAISS vector database.	17	Experimental	2	Hy
110	N2FlowJS/nbase NBase is a high-performance vector database for efficient similarity search,...	17	Experimental	2	TypeScript
111	haja-k/mysql-to-pgvector-embeddings vectorizing data from mysql database to vector so it can be used by LLM in...	17	Experimental	2	Python
112	cmessin02-cmyk/Sentry-Vector-The-AI-Powered-Immutable-Ledger A high-performance, C++ based Vector Database with HMAC-SHA256 blockchain...	16	Experimental	1	C++
113	mingyu-hkustgz/RESQ High-Ratio Vector Quantization	16	Experimental	10	C++
114	JGalego/VektorDB A minimal vector database for educational purposes.	16	Experimental	3	Python
115	SherifSystems/PythonVectorDB Pure Python vector database • int8 quantized • ~1100 QPS @ 50k vectors •...	15	Experimental	—	Python
116	matthewwangg/vector-database A performant in-memory vector database with an HNSW index, data persistence,...	15	Experimental	—	C++
117	kanitakadusic/bsc-thesis Vector Databases: Use Cases, Algorithms and Key Features	15	Experimental	—	TeX
118	hritik2002/local-vectordb Local vector database with embeddings & semantic search. Uses HNSW for fast...	15	Experimental	—	—
119	TekilaSS/Educational-Vector-Database 📚 Learn to build and understand Vector Databases step-by-step in Arabic,...	14	Experimental	—	Python
120	waynewbishop/quiver Quiver is a Swift package that provides vector mathematics, numerical...	14	Experimental	—	Swift
121	Linco2749/duckdb-s22 🦆 Explore DuckDB's powerful features for efficient data analysis and easy...	14	Experimental	—	—
122	deathbeam/vectorspace Directory file watcher for automatically creating and querying vector embeddings.	14	Experimental	4	Python
123	LongmaoTeamTf/ant Open-source vector database built to embedding similarity search	14	Experimental	10	Python
124	yichunzhao/python-learning Taking it slow and easy—Python, here I come. 🐍✨	14	Experimental	—	Python
125	AWeirdDev/vdb37 A simple vector database.	14	Experimental	1	Python
126	Ronakagrwal000/vector-cache-optimizer ⚡ Optimize vector searches with a hyper-efficient cache that uses machine...	14	Experimental	—	Python
127	yusupwinata/Basic-VectorDB Build vector database using LangChain, Hugging Face, Chroma and FAISS.	13	Experimental	2	Jupyter Notebook
128	JohnnyHyytiainen/glossary_db Personal Glossary Database to help keep track on terms and theory for school...	13	Experimental	2	Python
129	takurot/Pyrope Pyrope is a high-performance, adaptive Vector Database built as an extension...	13	Experimental	—	C#
130	gifton/VectorAccelerate Swift6 GPU-accelerated vector operations using Metal4 shaders for Apple...	13	Experimental	2	Swift
131	thkbit-labs/vecmodel A model-based, ORM-inspired abstraction for vector databases.	13	Experimental	2	Makefile
132	lcj2021/mini-ivf A cute toy of IVF (PQ).	13	Experimental	5	C++
133	gtfintechlab/Universal-NFT-Vector-Database The Universal NFT Vector Database: A Scalable Vector Database for NFT...	13	Experimental	7	Jupyter Notebook
134	starkdg/mvptree multiple vantage point distance-based tree data structure	13	Experimental	8	C++
135	jballo/vector-db-engine A FastAPI service that lets users create, read, update, and delete document...	12	Experimental	1	Python
136	RKirlew/SoraDB-A-Lightweight-Vector-Database SoraDB is a custom-built vector storage engine designed to manage and query...	12	Experimental	1	C++
137	colbertdb/colbertdb Open source ColBERT based document database	12	Experimental	3	Python
138	rosaia/vecworks Seamlessly manage vectorized data in Python	12	Experimental	1	Python
139	ocramz/vectordb Simple vector database based on annoy and sqlite3	12	Experimental	3	Python
140	B-R-P/VStore Embedded key-value store with vector similarity search	12	Experimental	1	Python
141	Maverick0351a/consciousdb ConsciousDB – Your Vector Database Is the Model	12	Experimental	1	Python
142	danilop/knn-search-algorithm-comparison KNN Search Algorithm Comparison – This project compares the performance of...	12	Experimental	4	Python
143	nathangtg/dbms-research This is the repository for ZGQ (Zone Graph Quantization)m Which is now...	12	Experimental	1	Python
144	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,...	12	Experimental	1	Go
145	patw/InstructorVec Create dense vectors using the instructor-large model, running on CPU in...	11	Experimental	—	Python
146	natenberenstein/deep-dive-databases Knowledge base covering database internals -- storage engines, data models,...	11	Experimental	—	—
147	tweedge/vectordb-docker-base Python 3.10-slim with VectorDB (vectordb2==0.1.9) and certain models...	11	Experimental	—	Dockerfile
148	RasaiStewart/Vector-database-using-vectordb My attempt to create a vector database to store the names of books I have...	11	Experimental	—	Python
149	tanushachoudhary/VectorDB A production-ready vector database system that stores document embeddings...	11	Experimental	—	Python
150	Flagro/VecMetaQ Server over Python Faiss serverless implementation to match interfaces used...	11	Experimental	2	Python
151	NautilusDB-cloud/nautilusdb-cli The simple client of NautilusDB, a Clound-Native Vector Search Service	11	Experimental	2	Python
152	1226085293/MiniVectorDB Lightweight, self-hosted Node.js vector database using WASM-based HNSW with...	11	Experimental	—	TypeScript
153	timothyckl/iota a minimal local embedding database.	11	Experimental	2	Python
154	FoxRav/RL-astradb- Astra Vector DB on Python-paketti, joka tallentaa dokumentteja DataStax...	11	Experimental	—	Python
155	yezz123/vectorai A Vector Database REST API with custom indexing algorithms	10	Experimental	4	Python
156	mingyu-hkustgz/LabelANN Label Filtering Vector Similarity Search	10	Experimental	4	C++
157	Md-Emon-Hasan/Vector-Database Designed to store and retrieve high-dimensional data, such as embeddings,...	10	Experimental	1	Jupyter Notebook

Comparisons in this category

nano-vectordb and vectordb (60 vs 50)