Open-source alternatives to Hnsw

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

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

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

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

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

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

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

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

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

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

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

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

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

Vector similarity search extension for PostgreSQL.

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

Pinot is a distributed, columnar analytical database designed for high-concurrency, low-latency query processing. It functions as a real-time OLAP datastore, enabling interactive, user-facing analytics by ingesting and querying massive datasets from both streaming and batch sources. The system architecture relies on a centralized controller for cluster coordination and a distributed segment-based storage model to ensure horizontal scalability. The platform distinguishes itself through a hybrid ingestion pipeline that unifies real-time event streams and historical batch data into a single quer

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

This project is a high-performance library designed for the similarity search and clustering of dense vectors across massive datasets. It functions as a vector similarity search engine, providing the necessary tools to organize complex numerical data into specialized structures that facilitate rapid retrieval and efficient querying of millions of records. The library distinguishes itself through a variety of advanced indexing and compression techniques, including hierarchical navigable small worlds for logarithmic time complexity and inverted file indexing to partition vector spaces into mana

Hazelcast is a distributed data platform that combines an in-memory data grid with a stream processing engine to support real-time analytics and event-driven applications. It functions as a partitioned, distributed key-value store that replicates data across cluster nodes to provide low-latency access and high availability. The platform also serves as a distributed SQL query engine, allowing users to execute standard SQL statements against both in-memory datasets and external data sources. What distinguishes Hazelcast is its use of a distributed consensus subsystem to maintain strongly consis

This platform is an automated documentation and codebase analysis system designed to generate structured wikis, technical guides, and interactive diagrams from source code repositories. It functions as a retrieval-augmented generation framework that connects codebases to language models, enabling context-aware answers, deep research, and automated documentation updates through semantic vector search. The system distinguishes itself through a self-hosted, containerized architecture that supports both cloud-based and local AI model execution. It provides sophisticated model orchestration, allow

Scira is an AI-powered search and synthesis engine that uses agentic research workflows to find and organize information from the web and academic sources. The system breaks complex queries into multi-step plans and generates grounded answers with inline citations for verification. The platform distinguishes itself by executing Python code within isolated sandboxes to perform data analysis and create visual charts from retrieved data. It also implements retrieval-augmented generation to perform semantic searches across uploaded documents, including PDFs and CSV files, and integrates with clou

Daft is a distributed dataframe library and multimodal data processor designed to handle large-scale structured and unstructured data. It functions as a vectorized execution engine that processes tables alongside images, audio, and video, utilizing a unified schema to manage diverse data types. The project distinguishes itself by combining distributed data engineering with large-scale AI inference. It provides an AI data pipeline for batch-optimizing model prompts and generating high-dimensional text embeddings, while utilizing zero-copy memory sharing to execute custom Python functions witho

Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut

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

Cult-UI is an AI application UI kit and a collection of accessible components and templates designed for building large language model powered interfaces and agent workflows. It provides a foundation for developing AI applications, including specialized interface libraries for retrieval-augmented generation and agent orchestration. The project distinguishes itself through dedicated UI building blocks for coordinating multi-agent systems, evaluator-optimizer loops, and tool-based execution flows. It also features a component installation CLI and model context protocols for rapidly integrating