Data, search & knowledge

Vector databases & semantic search

Vector databases and semantic search projects store and retrieve embeddings so other agents can search by meaning rather than exact keywords. Some run as standalone vector databases such as Milvus, while others bundle indexing and retrieval into a single tool, as xerj does by combining BM25 full-text, vector, and hybrid search over code, documents, and logs.

1,175 agents · most starred first

Top 100 of 1,175

milvus★ 46,706

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

tidb★ 40,756

TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.

chroma★ 29,715

Search infrastructure for AI

xerj★ 18,993

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

turbovec★ 17,503

A vector index built on TurboQuant, written in Rust with Python bindings

zvec★ 16,273

A lightweight, lightning-fast, in-process vector database

clip-as-service★ 12,841

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

deeplake★ 9,271

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

postgresml★ 6,831

Postgres with GPUs for ML/AI apps.

helix-db★ 6,304

HelixDB is an OLTP graph database with native vector and full-text search built in Rust on Object Storage.

infinity★ 4,770

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

RuVector★ 4,714

RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.

fastembed★ 3,305

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

seekdb★ 3,253

The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.

examples★ 3,047

Jupyter Notebooks to help you get hands-on with Pinecone vector databases

bootcamp★ 2,454

Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

beir★ 2,334

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

vearch★ 2,333

Distributed vector search for AI-native applications

vector-admin★ 2,242

The universal tool suite for vector database management. Manage Pinecone, Chroma, Qdrant, Weaviate and more vector databases with ease.

matrixone★ 2,068

AI-native HTAP database with Git-for-Data and built-in vector search, serving as the data and memory backbone for intelligent agents and applications.

bm25s★ 1,827

Fast BM25 search in Python, powered by Numpy and Numba

korvus★ 1,473

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

hyperDB★ 1,399

A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.

wink-nlp★ 1,391

Developer friendly Natural Language Processing ✨

EmbedAnything★ 1,333

Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

UForm★ 1,252

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

osgrep★ 1,142

Open Source Semantic Search for your AI Agent

RAG-Retrieval★ 1,139

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

chromem-go★ 1,075

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.

swiss_army_llama★ 1,053

A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

fastembed-rs★ 1,052

Rust library for generating vector embeddings and reranking locally!

MyScaleDB★ 1,040

A @ClickHouse fork that supports high-performance vector search and full-text search.

FlashRank★ 1,015

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

fastembed-rs★ 1,007

Rust library for generating vector embeddings and reranking locally!

vectordb-recipes★ 991

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

pylate★ 914

Late Interaction Models Training & Retrieval

vectordb★ 874

A high performance Vector Database leveraging parallel graph computing

NeumAI★ 868

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

byaldi★ 852

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

pg_vectorize★ 835

Full-text and semantic search on any Postgres

moss★ 828

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

semantic-search-nextjs-pinecone-langchain-chatgpt★ 760

Embeds text files into vectors, stores them on Pinecone, and enables semantic search using GPT3 and Langchain in a Next.js UI

VLM2Vec★ 705

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

RankGPT★ 666

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

next-plaid★ 623

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

AnglE★ 576

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

caiss★ 550

一款简单好用的 跨平台/多语言的 相似向量/相似词/相似句 高性能检索引擎。欢迎star & fork。Build together! Power another !

aifs★ 462

Local semantic search. Stupidly simple.

python-sdk★ 456

Official Python SDK for the Pinecone vector database

mlx-embeddings★ 454

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

redis-vl-python★ 436

Redis Vector Library. The AI-native Python client for Redis.

easy-vecdb★ 434

📚 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/

unisondb★ 429

A streaming multimodal database for Edge AI, and Edge Computing.

DCI-Agent-Lite★ 424

[NeurIPS 2026 Spotlight] Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

primer-llm-embedding★ 381

static region:us

VecturaKit★ 328

Swift-based vector database for on-device RAG using MLTensor and MLX Embedders

langconnect-client★ 325

A Modern GUI Interface for Vector Database Management(Supports MCP integration)

semantic-cache★ 305

A fuzzy key value store based on semantic similarity rather lexical equality.

OpenConstructionEstimate-DDC-CWICR★ 289

Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 30 regions. Semantic search via Qdrant vector DB

chromadb-admin★ 282

Admin UI for Chroma embedding database built with Next.js

vidore-benchmark★ 278

Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

vectordbz★ 275

A modern desktop application for exploring, managing, and analyzing vector databases

skills★ 271

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java

vector-storage★ 249

Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to convert documents into vectors and allows searching for similar documents based on cosine similarity.

satoriDB★ 245

High performance embedded vector database

k8ssandra-operator★ 244

The Kubernetes operator for K8ssandra

ScalableVectorSearch★ 242
pgvector_pgsql_windows★ 234

pgvector for PostgreSQL Windows (native compiled in Microsoft Windows environment)

python★ 233

Python client for Antarys vector database, optimized for large-scale vector operations with built-in caching, parallel processing, and dimension validation.

client-vector-search★ 230

A client side vector search library that can embed, store, search, and cache vectors. Works on the browser and node. It outperforms OpenAI's text-embedding-ada-002 and is way faster than Pinecone and other VectorDBs.

guardian-db★ 214

GuardianDB: High-performance, local-first decentralized database that stores and processes data, built on Rust and Iroh

nano-vectordb★ 211

A simple, easy-to-hack Vector Database

VecTextSearch★ 206

一个99%由OpenAI ChatGPT开发的项目。A project that is 99% developed by OpenAI ChatGPT.

ShannonBase★ 200

The Next-Gen Database for AI—an infrastructure designed for data and AI. As the MySQL of the AI era.

headless-vector-search★ 198

Supabase Toolkit to perform vector similarity search on your knowledge base embeddings.

TriviumDB★ 192

A lightweight embedded database engine that natively fuses vector search, graph, and document-oriented metadata within a single storage kernel — ready to use the moment data is written.

fastembed-js★ 177

Generate vector embeddings in NodeJS

fastembed-js★ 177

Generate vector embeddings in NodeJS

open-text-embeddings★ 174

Open Source Text Embedding Models with OpenAI Compatible API

mememo★ 167

A JavaScript library that brings vector search and RAG to your browser!

yc-idea-matcher★ 166

Submit your idea and get a list of similar ideas that YCombinator has invested in in the past.

SwiftSemanticSearch★ 162

Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera capture using USearch & UForm AI Swift SDKs for Apple devices 🍏

infino★ 157

Search library built on Parquet. Fast, efficient, and scalable.

redis-arXiv-search★ 155

Vector search demo with the arXiv paper dataset, RedisVL, HuggingFace, OpenAI, Cohere, FastAPI, React, and Redis.

duckdb-embedding-search★ 153

Fast similarity search using DuckDB

semantic-search-openai-pinecone★ 152

Semantic search with openai's embeddings stored to pineconedb (vector database)

VectorRAG.Net★ 149

VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieval-Augmented Generation). Core search is based on Random Hyperplane LSH candidate generation with exact rerank by dot/cosine.

SharpVector★ 147

Lightweight, In-memory, Semantic Search, Text Vector Database to embed in any .NET Application

litepali★ 132

LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing, optimized for cloud deployment.

weightgain★ 129

Train an adapter for any embedding model in under a minute

vector-cookbook★ 129

Timescale Vector Cookbook. A collection of recipes to build applications with LLMs using PostgreSQL and Timescale Vector.

semantic-search-app-template★ 115

Tutorial and template for a semantic search app powered by the Atlas Embedding Database, Langchain, OpenAI and FastAPI

fluid-db★ 113

Fluid Database

LodeDB★ 107

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

fastembed-go★ 104

Go implementation of @qdrant/fastembed.

fastembed-go★ 103

Go implementation of @qdrant/fastembed.

brinicle★ 101

A resource-efficient C++ vector index engine built for low-RAM production workloads

edgevec★ 100

High-performance vector search for Browser, Node, and Edge

oasisdb★ 99

OasisDB: A minimal and lightweight vector database

cortrix★ 99

Semantic storage for AI agents. Active pre-release.

More in Data, search & knowledge