Open-source alternatives to Reactivesearch

Marqo is an ecommerce product discovery platform, multimodal vector database, and AI search merchandising tool. It provides infrastructure for implementing semantic search and recommendations, allowing shoppers to find products using natural language and images. The platform distinguishes itself through a hybrid ranking pipeline that combines neural semantic scores with business-defined boosting and pinning rules. It features a conversational commerce engine that uses large language models to process user intent and provides a search performance analytics suite for measuring conversion uplift

This project is a software development kit and cluster management tool for PHP. It serves as a full-text search SDK and vector search interface, enabling applications to perform lexical, fuzzy, and semantic searches against indexed data. The library implements a PSR 7 HTTP client to ensure cross-environment compatibility through standardized messaging interfaces. It provides a specialized interface for retrieving embeddings and performing semantic retrieval workflows using vector data. Its capability surface covers a wide range of administrative and operational tasks, including search index

This project is a Node.js client and database driver for Elasticsearch. It acts as a REST API wrapper that translates JavaScript method calls into HTTP requests to index, search, and manage documents within a distributed search and analytics engine. The library provides a programmatic interface for cluster management and data integration. It includes tools for discovering cluster nodes and managing indices to maintain connection stability and organize data storage. The client covers a broad range of operations, including document lifecycle management for CRUD actions, search query execution,

Searchkick is an integration library and wrapper that connects application models to search engines such as Elasticsearch and OpenSearch. It functions as a search index synchronizer, automatically mirroring database records to a search server to enable full-text and vector retrieval. The project provides a high-level interface for implementing keyword search, semantic vector search, and hybrid search. It distinguishes itself through the ability to combine traditional keyword matching with vector embeddings using reranking and fusion techniques to improve precision. The library covers the end

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

GreptimeDB is a distributed, open-source time-series database built for unified observability. It stores and queries metrics, logs, and traces together in a single columnar engine, supporting both SQL and PromQL for analysis. The database is designed as a Kubernetes-native operator with a decoupled compute and storage architecture, enabling horizontal scaling and multi-region deployment. What distinguishes GreptimeDB is its role as a multi-protocol ingestion gateway, accepting data through OpenTelemetry, Prometheus Remote Write, InfluxDB, Loki, Elasticsearch, Kafka, and MQTT protocols without

bqplot is an interactive data visualization library for Jupyter notebooks. It implements a grammar of graphics model, allowing users to build complex 2D charts by combining marks, scales, and axes. The library distinguishes itself with specialized toolkits for financial charting, such as OHLC candlesticks and time-series analysis, and geographic data visualization, including choropleths and custom map projections for TopoJSON and GeoJSON data. It enables deep interaction through tools like lasso selection, rectangular brushing, and the ability to manually manipulate plot points or line data.

This project is a Go client library and API wrapper for interacting with Elasticsearch clusters. It serves as a programmatic interface for managing documents, indices, and cluster health, allowing Go applications to perform search and indexing operations via the REST API. The library functions as a distributed search orchestrator, providing specialized tools for high-throughput data ingestion and cluster administration. It features a buffered bulk processor with exponential backoff retries for optimizing write performance and supports automated index lifecycle transitions and historical data

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

Superlinked is a development framework designed for building semantic search and retrieval pipelines. It functions as a machine learning data pipeline and semantic retrieval engine, providing the tools necessary to unify data schema definition, embedding generation, and vector database integration within a single application. The framework distinguishes itself by acting as a vector database orchestrator that manages the lifecycle of machine learning models alongside complex search logic. It enables developers to construct structured data models that map raw content and metadata into unified r

Zinc is a high-performance full-text search engine written in Go. It provides a schema-less document index that organizes arbitrary datasets into searchable structures without requiring a predefined data format. The engine features an API compatible with Elasticsearch for indexing and querying data, which facilitates the ingestion of single and bulk records. It is designed as an in-process search engine that embeds indexing and retrieval logic within a single binary to operate with minimal system resource overhead. The system includes a built-in web-based management interface for executing s

Rags is an orchestration tool for building retrieval-augmented generation pipelines and managing conversational data interfaces. It serves as a system for creating these pipelines from local files and web pages using natural language instructions to query, retrieve, and summarize information from connected datasets. The project features a multimodal retrieval system that identifies and extracts information across different data types and modalities. It includes a vector search orchestrator to manage chunking strategies and search parameters, alongside a pipeline builder that translates conver

This project is a collection of generative AI implementations focused on the development of AI agents, retrieval-augmented generation pipelines, and vector search integration. It provides a framework for connecting managed cloud databases to language models to create context-aware applications. The project covers the orchestration of autonomous agents that use multi-step reasoning and external tools to complete tasks. It includes implementations for semantic retrieval using high-dimensional embeddings and the use of model-agnostic prompting to ensure consistent outputs across different large

Omi is an open-source wearable AI platform that captures audio and screen data to provide real-time conversational assistance and memory. It integrates a wearable hardware development kit with a vector memory database and large language model capabilities to create a persistent digital record of user interactions. The platform is distinguished by its BLE audio streaming pipeline, which transmits raw audio from wearable hardware for real-time transcription and speaker identification. It utilizes a plugin-based agent tool framework that allows AI assistants to autonomously invoke custom functio

Colanode is a local-first collaboration platform designed for shared documents, chat, and databases. It provides a self-hosted suite for team collaboration and knowledge management, allowing users to maintain full control over their data and privacy on their own infrastructure. The platform is distinguished by a synchronization engine that uses WebSockets for real-time data broadcasting and a local-first approach to ensure work continues offline. It incorporates AI-powered retrieval through vector-based semantic search, enabling users to find information based on meaning across documents and

Wego is a terminal-based weather client and dashboard that functions as an API wrapper for retrieving atmospheric data. It provides a command-line interface for accessing current weather conditions and multi-day forecasts across various provider backends. The tool features a provider-based abstraction to decouple data retrieval from specific API implementations and utilizes disk-based response caching to reduce redundant network requests. It supports local configuration storage for persisting API credentials and preferred locations across separate command executions. The system includes capa

Superagent is a framework for AI assistant orchestration and agent security. It provides the tools to build intelligent assistants that integrate external APIs and maintain conversation memory to automate complex tasks. The project focuses on AI agent security through adversarial testing, red teaming, and the detection of prompt injections and malicious tool calls. It includes automated vulnerability patching, which scans codebases and configurations for security flaws and generates pull requests with fixes. The platform supports retrieval augmented generation by connecting language models t

ChatterBot is a conversational AI framework and machine learning dialogue system used to build bots that generate automated responses. It functions as a multilingual natural language processing library and a vector-based knowledge base, utilizing logic adapters and statistical pattern matching to select the most confident response to user input. The system supports multilingual chatbot training and processing by using a design independent of specific linguistic rules. It employs semantic vector search to retrieve contextually accurate responses from a database of stored conversations and can

koanf is a configuration management library for Go designed to load, merge, and unmarshal application settings from multiple sources into structured objects. It functions as a multi-source config loader that aggregates data from environment variables, files, and remote providers into a single unified map. The system utilizes a pluggable architecture for parsing and data abstraction, allowing it to transform bytes from formats such as JSON, YAML, and TOML into nested maps. It supports dynamic configuration watching to monitor external sources and trigger automatic reloads when settings change.

Telegram Search is a self-hosted platform designed to export, index, and archive personal or group message history. It functions as a private search engine that transforms scattered communication logs and media assets into a searchable knowledge library, allowing users to maintain full control over their data through containerized infrastructure. The platform distinguishes itself by utilizing vector-based semantic indexing to enable fuzzy retrieval across historical datasets. It incorporates an optical character recognition pipeline to extract text from images and media files, ensuring that v

Chonkie is a text chunking library designed for retrieval-augmented generation pipelines. It functions as a semantic text splitter and RAG ingestion pipeline, transforming raw text into embedded segments for storage in vector databases. The project distinguishes itself through specialized splitting strategies, including an AST-based code splitter for preserving logical boundaries in source code and a semantic text splitter that uses embedding models to determine boundaries based on meaning. It also provides a vector database ingestor to automate the generation of embeddings and their export t

OpenRAG is an agentic retrieval-augmented generation framework and containerized stack. It provides a vector search engine for indexing unstructured documents and a Model Context Protocol server that exposes ingestion and semantic search tools to external AI assistants. The system distinguishes itself through a visual AI orchestration interface, allowing users to build retrieval pipelines via a drag-and-drop designer rather than manual code. It utilizes agentic workflows that coordinate multiple agents and re-ranking steps to improve response accuracy, and it allows the definition of agent sk

Elasticsearch-HQ is a web-based management interface used to monitor and administer Elasticsearch clusters, indices, and nodes through a graphical dashboard. It serves as an API proxy for executing REST requests and managing cluster data and metadata. The project provides centralized multi-cluster orchestration, allowing administrators to manage several remote instances from a single interface. It includes specialized managers for index lifecycle control, snapshot repository backup management, and real-time health tracking for node performance and shard stability. The platform covers a broad

This project is a knowledge base plugin and RAG context manager that uses a local vector database interface to enable semantic search and relationship mapping. It transforms text into numerical vectors to find semantically related notes and excerpts based on conceptual meaning rather than keyword matches. The system differentiates itself through a semantic graph visualizer that maps notes into clusters to reveal conceptual connections. It also features a context manager capable of bundling local notes and excerpts into reusable packs to provide grounded factual bases for large language model

document.ai is a local document question-answering system and vector database search engine. It functions as a retrieval-augmented generation knowledge base that combines a vector database with language models to generate answers grounded in private local datasets. The project features a domain-specific embedding pipeline and a fine-tuned language model framework. These tools allow for the use of specialized embedding models and mathematical theme extraction to improve retrieval accuracy for professional terminology and technical subject areas. The system covers vector-based semantic retriev

llm-zoomcamp is a comprehensive educational program and course for building real-life AI systems using large language models. It serves as a structured curriculum and implementation guide for developing AI applications and retrieval techniques. The project provides instructional material on building retrieval augmented generation pipelines to ground model responses in custom knowledge bases. It includes training on vector database implementation, semantic search, and the use of function calling to create autonomous agentic workflows. The curriculum covers a broad range of system development