Open-source alternatives to Hnswlib

zvec is an embedded vector database engine and indexing library designed for high-dimensional similarity search. It functions as a hybrid search engine and a retrieval-augmented generation knowledge base, allowing for the storage and retrieval of dense and sparse vectors. The system is distinguished by its hybrid retrieval pipeline, which fuses vector similarity, full-text keyword matching, and scalar metadata filtering into single query operations. It supports a plugin-based model integration system for registering custom embedding models and rerankers, as well as language bindings for nativ

Hora is a vector similarity search library written in Rust designed for efficient approximate nearest neighbor retrieval in high-dimensional data spaces. It functions as a compiled search engine that organizes vector spaces using hierarchical graphs, trees, and product quantization, while computing proximity through various mathematical distance formulas including Euclidean, Manhattan, cosine, and dot product calculations. The library supports high-performance execution through hardware-accelerated instruction sets and concurrent thread dispatch across multiple hardware processors. To accommo

SPTAG is a vector approximate nearest neighbor search library and distributed vector search engine. It provides a large-scale vector index designed to organize and retrieve similar vectors from massive datasets using high-performance similarity search and proximity queries. The system functions as a dynamic vector index manager, supporting incremental updates, insertions, and deletions of vectors without requiring a full index rebuild. It scales search operations across multiple machines to handle large-scale datasets and high volumes of online requests through distributed search request hand

Redis is a high-performance in-memory key-value store that functions as a distributed cache, message broker, and NoSQL database. It provides sub-millisecond read and write access to data stored in RAM and can operate as a vector database for indexing high-dimensional embeddings. The system supports a wide range of data storage and synchronization primitives, including the management of strings, hashes, lists, sets, and JSON documents. It enables real-time data operations through atomic transactions, hybrid persistence using snapshots and append-only logs, and high-availability configurations

Kùzu is an embedded property graph database engine designed for high-performance analytical queries and local data management. It operates as a library within the host application process, utilizing a columnar-based storage architecture and just-in-time query compilation to execute complex graph traversals and pattern matching efficiently. By mapping database files directly into system memory, it ensures data durability and high-speed access while maintaining ACID-compliant transactional integrity. The engine distinguishes itself by integrating vector similarity search and full-text search di

This project is a feature-rich Go client library designed for interacting with Redis. It serves as a comprehensive interface for managing remote data stores, enabling developers to execute standard database commands, handle complex data structures, and perform asynchronous operations within Go applications. The library distinguishes itself through its support for advanced Redis capabilities, including connection pooling, pipelining, and transactional integrity. It provides specialized primitives for managing distributed clusters, including automated topology updates and request routing to sha

Deepface is a comprehensive deep learning library for facial recognition and demographic analysis. It provides a modular pipeline that handles the entire lifecycle of facial processing, including detection, geometric alignment, and the transformation of facial images into high-dimensional numerical vector embeddings for identity verification and similarity comparison. The library distinguishes itself through a model ensemble approach, which combines predictions from multiple pre-trained neural networks to improve classification accuracy and reduce bias. It also integrates advanced security fe

Annoy is a C++ library designed for approximate nearest neighbor search in high-dimensional vector spaces. It functions as a vector similarity search engine that constructs static, disk-based data structures to facilitate fast lookups. By mapping identifiers to vector data and persisting these structures to disk, the library enables efficient, memory-mapped access to large datasets. The project distinguishes itself through the use of random projection trees and distance-metric-based partitioning, which organize data into hierarchical binary trees to balance search precision against computatio

cuml is a GPU-accelerated machine learning library and framework that uses CUDA to accelerate tabular data preprocessing and model execution. It provides a suite of tools for training and deploying classification, regression, and clustering models on NVIDIA GPUs and GPU clusters. The library is designed for scalability, offering a distributed GPU machine learning environment that can spread computation and data across multiple hardware accelerators and nodes to handle datasets exceeding single-device memory. It mirrors standard estimator interfaces to allow the replacement of CPU-based models

mlpack is a header-only C++ machine learning library that defines matrix types as compile-time templates, enabling flexible numeric precision and memory layout without runtime overhead. Its core identity is built around a template metaprogramming architecture that allows algorithms to be included selectively as independent modules, reducing binary size, and supports compile-time serialization of neural network parameters by deducing matrix types and structure at compile time. The library distinguishes itself through a multi-language binding framework that automatically generates bindings for

Qdrant is a high-performance vector similarity database designed to store, index, and search high-dimensional vectors alongside structured metadata. It functions as a distributed search engine that manages large-scale data clusters, providing low-latency retrieval and complex filtering capabilities. The system is built to serve as a specialized middleware layer, connecting machine learning pipelines and AI agents to persistent storage for intelligent information retrieval and recommendation tasks. The platform distinguishes itself through advanced retrieval techniques, including support for h

pgai is a PostgreSQL AI toolkit and framework designed to integrate large language models and vector embeddings directly into a database. It serves as a bridge for executing machine learning model requests and performing text-to-SQL translations within standard database queries. The project provides an automated vector embedding pipeline that handles the loading, parsing, and chunking of text from tables and unstructured documents. This system utilizes a background worker to synchronize embeddings automatically as source data changes and includes specialized tools for building retrieval-augme

This project is a legal AI system that provides a language model assistant grounded in a retrieval-augmented generation knowledge base. It enables users to perform vector-based legal searches and receive grounded answers to legal questions. The system specifically supports Chinese legal knowledge retrieval by converting markdown documents into vector embeddings for semantic search. It utilizes a streaming web interface that delivers incremental AI responses via server-sent events. The broader capability surface includes chunk-based document processing, vector-based knowledge indexing, and si

Memvid is an embedded memory framework designed to provide persistent, versioned context for intelligent agents. It functions as a local vector database library that stores all data within a single binary file, removing the need for external database infrastructure or network dependencies. The system distinguishes itself by integrating in-process vector indexing with append-only versioning, allowing for high-speed semantic similarity searches alongside the ability to track and roll back state changes over time. It includes built-in transparent data encryption and masking to secure sensitive i

Chroma is a specialized vector database designed to index and retrieve high-dimensional data representations for semantic similarity search. It functions as a comprehensive platform for information retrieval, enabling the storage and management of unstructured documents alongside structured metadata. By mapping data into numerical representations, the system facilitates rapid similarity lookups across large datasets. The platform distinguishes itself through a hybrid search infrastructure that combines dense vector embeddings with sparse keyword and regular expression matching to balance sema

Embedding Atlas is a web-based interface for rendering high-dimensional vector embeddings and analyzing complex datasets through interactive visual clustering. It functions as a high-dimensional data analyzer used to discover trends and density patterns, acting as a vector similarity explorer to locate nearest neighbor data points within large-scale embedding datasets. The project provides a synchronized multimodal data dashboard that links tabular data with images, audio, and text. It utilizes hardware-accelerated rendering to display millions of embedding points and employs high-dimensional

Weaviate is an AI-native vector database designed to store and index high-dimensional vector embeddings alongside traditional data objects. It serves as a backend infrastructure for retrieval-augmented generation, enabling applications to ground language model responses in private, context-aware data. The platform distinguishes itself by combining vector similarity search with traditional keyword filtering through a hybrid storage architecture. It integrates directly with external machine learning models to automate the generation of embeddings and perform complex inference tasks during inges

Databend is a cloud-native data warehouse and OLAP database designed for large-scale analytics. It functions as a SQL-compliant engine and serverless analytics platform that separates compute from storage to allow for independent scaling. The system integrates vector database capabilities, indexing high-dimensional embeddings to enable semantic, hybrid, and full-text searches across massive datasets. It further distinguishes itself through serverless compute management that automatically scales resources based on demand and shuts them down during idle periods. The platform covers a broad set

PostgresML is a machine learning database extension for PostgreSQL that integrates model training and inference directly into the database. It functions as an in-database AI platform and vector database, enabling the execution of large language models and natural language processing tasks on stored records without exporting data to external services. The system distinguishes itself by utilizing GPU acceleration to minimize latency during model predictions and employing a hybrid storage engine that maintains relational data alongside high-dimensional vectors. It allows for the building and fin

This project is a collection of educational resources and technical guides focused on the development and implementation of large language models. It provides a comprehensive curriculum covering transformer architectures, training methods, and deployment strategies. The materials provide detailed instructions for building autonomous agents using reasoning loops and tool integration, as well as guides for fine-tuning models through supervised learning and preference optimization. It also includes tutorials for constructing retrieval augmented generation pipelines and implementing transformer m

Vector similarity search extension for PostgreSQL.

Gensim is a natural language processing toolkit designed for large-scale text analysis and the training of semantic vector embeddings. It provides a framework for identifying latent thematic structures within document collections and calculating semantic similarity between text segments using unsupervised statistical algorithms. The project is distinguished by its ability to handle datasets that exceed available system memory through incremental corpus streaming, which processes documents one at a time from disk. It utilizes sparse vector representations and dictionary-based token mapping to

X-algorithm is a modular recommendation engine framework designed to orchestrate personalized content feeds. It functions as a machine learning ranking system that manages the end-to-end lifecycle of content delivery, from initial candidate retrieval to final display ordering. The system distinguishes itself through a multi-stage pipeline that integrates vector-based similarity search with transformer-based engagement prediction. By mapping user history and content features into high-dimensional embeddings, it performs rapid approximate nearest neighbor searches to identify relevant items. Th

Infinity is a distributed vector database and multimodal vector store designed to manage large-scale datasets for retrieval and similarity search. It serves as a backend for large language model applications and retrieval augmented generation pipelines by storing and retrieving dense vectors, sparse vectors, and full-text data. The system functions as a hybrid search engine, combining vector embeddings and full-text search with reranking algorithms to identify the most relevant documents. It supports multimodal data storage, allowing the maintenance of diverse data types including tensors, st

This project is a full text search engine and enterprise search infrastructure designed for indexing and retrieving large sets of documents. It provides a comprehensive framework for information discovery using ranked results and linguistic analysis. The system integrates high-dimensional vector similarity search for semantic retrieval alongside traditional full-text capabilities. It distinguishes itself through support for geospatial data retrieval, multilingual text processing, and a search suggestion workflow that includes typo-tolerant query completion and spellchecking. The platform cov

RediSearch is a Redis module that adds secondary indexing, full-text search, aggregation, and vector similarity search directly into the in-memory data store. It operates as an in-process search engine, extending the core key-value store with capabilities for indexing hash and JSON documents, enabling fast field-level lookups beyond primary key access. The module provides a full-text search engine built on inverted indexes, supporting stemming, fuzzy matching, and relevance scoring via tf-idf. It also includes a vector similarity search engine using a Hierarchical Navigable Small World graph

TensorFlow Similarity is a Python framework designed for training neural networks to learn high-dimensional vector representations and perform similarity-based retrieval. It provides a comprehensive toolkit for metric learning, enabling the development of systems that group similar items together in vector space and identify them through distance-based comparisons. The library distinguishes itself by integrating specialized training techniques, such as contrastive and triplet-based learning, with robust data management tools that ensure stable model convergence. It supports self-supervised re