embeddable vector database / similarity search
Zvec is a lightweight, in-process vector database for embedding low-latency similarity search directly into applications.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
embedded Rust retrieval library; choose for multimodal data and serverless in-process vector search.
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
in-process TypeScript search/RAG library; choose for browser/edge apps with tiny bundle size.
🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
Rust in-process vector/lexical search library; choose for Rust-native apps needing both without a server.
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
server-based hybrid search engine; choose when you need full-text + vector API and don't require in-process embedding.
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
Postgres extension for full-text/vector; choose when already on Postgres and want unified queries.
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
distributed AI search platform; choose for large-scale ranking/low-latency serving over embedded use.
The AI search platform
OLTP graph-vector database on object storage; choose for graph+vector workloads at scale.
HelixDB is an OLTP graph-vector database built in Rust on Object Storage.
AI-native server with hybrid dense/sparse/tensor search; choose for RAG needing server-based multi-vector search.
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
AI-native search database server; choose for agent storage unifying vector and structured data.
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.
data-structure server with vector query; choose when using Redis as cache and need lightweight vector search.
For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
standalone vector DB server; choose for production-scale vector search with rich filtering.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Postgres extension for vector similarity; choose when staying with Postgres and want SQL vector search.
Open-source vector similarity search for Postgres
vector database server with object storage; choose for scalable multi-tenant vector search with filters.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
in-memory full-text/vector search server; choose for typo-tolerant search UX in front-end apps.
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
search database with SQL and real-time indexing; choose for hybrid full-text/vector on a server.
Open-source search database for full-text, vector, and hybrid search with real-time indexing and SQL.
Postgres extension for DiskANN-based vector search; choose to scale pgvector on Postgres.
Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.
standalone vector DB management system; choose for a GPL-licensed server-based vector search.
Epsilla is a high performance Vector Database Management System
distributed vector search server; choose for AI-native distributed vector search at scale.
Distributed vector search for AI-native applications
PostgreSQL vector extension; choose if committed to Postgres despite stalled maintenance.
PostgreSQL vector database extension for building AI applications
These projects were analysed and named zvec among their alternatives. The relationship is not symmetric — how zvec rates them is a separate judgement, made when zvec is analysed in its own right.
calls zvec “Choose when you want an in-process vector index with minimal overhead and no network service.”
For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
calls zvec “choose for an in-process lightweight vector DB when you don't need a server, at the cost of true distributed scale.”
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
calls zvec “Choose when you need an in-process, lightweight vector database library for low-latency applications without a separate server.”
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
calls zvec “choose for a lightweight in-process vector database with low overhead.”
Open-source vector similarity search for Postgres
calls zvec “Choose when you need an in-process, lightweight vector database embedded directly in your application.”
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
calls zvec “Choose zvec when you want an ultra-lightweight embedded vector index in your application and do not need full-text search or a server.”
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
calls zvec “choose when you need a lightweight embedded vector index only, with no server and no full-text search”
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
calls zvec “Choose for an in-process lightweight vector database in C++; vector-only, no server or SQL.”
Open-source search database for full-text, vector, and hybrid search with real-time indexing and SQL.
calls zvec “Lightweight in-process vector database; choose it for simple embedded vector search without Lance's multimodal lakehouse.”
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
calls zvec “In-process vector-only database; choose when you need lightweight embedded vector search but no full-text/hybrid.”
🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
calls zvec “Choose it when you need a lightweight in-process vector database only, without full-text search or analytics.”
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
calls zvec “Embedded vector database for lightweight in-process ANN; no server features or text ranking.”
The AI search platform