Open-source self-hosted vector db
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 9 |
| Companies | 48 |
| Part of | ai data |
| Map changed | 2026-08-29 |
| Map | open the map |
Open-source self-hosted vector db is a territory of the AI industry on map of ai. In short: open-source self-hosted vector databases store and search high-dimensional vector embeddings to find similar items by semantic meaning. The map lists 48 products and companies in 9 categories.
The map of open-source self-hosted vector db has 9 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
purpose-built vector databases8 products and companies
Open-source vector databases optimized for semantic search and embeddings, self-hosted on your infrastructure. Used by developers building AI applications, RAG systems, and semantic search features.
Open ground
Most open-source vector DBs lack enterprise-grade observability and cost optimization for multi-tenant deployments at scale.
approximate nearest neighbor libraries6 products and companies · its own article →
Approximate nearest neighbor libraries enable fast similarity search in high-dimensional vector spaces, essential for AI applications like semantic search, recommendation systems, and RAG pipelines. Used by ML engineers, data scientists, and AI product teams.
relational databases with vector extensions5 products and companies · its own article →
Relational databases enhanced with vector search capabilities for storing and querying embeddings alongside traditional data. Used by developers building AI applications, semantic search, and recommendation systems without separate vector DB infrastructure.
Products and companies
full-text and hybrid search engines7 products and companies
Open-source self-hosted vector databases that enable full-text and hybrid search capabilities by combining semantic and keyword matching. Used by developers building AI applications, retrieval-augmented generation systems, and enterprise search solutions requiring data privacy and control.
Products and companies
in-process embedded vector stores4 products and companies
In-process embedded vector stores are lightweight database engines that run directly within applications to store and query vector embeddings without external infrastructure. Developers and edge applications use them for semantic search, RAG systems, and local AI features.
Products and companies
real-time and cache-layer vector stores4 products and companies
Open-source self-hosted vector databases that enable real-time similarity search and semantic caching for AI applications. Used by developers building LLM applications, RAG systems, and semantic search features who need full control over infrastructure.
Products and companies: redis (redisearch), valkey, apache cassandra with vector, kurrentdb.
rag frameworks and orchestration5 products and companies · its own article →
Open-source self-hosted vector databases that run on user infrastructure without vendor lock-in. Data engineers, ML teams, and organizations with data residency requirements deploy these to store and retrieve high-dimensional vectors.
Products and companies: langchain, llamaindex, haystack, dify, ragflow.
embedding models5 products and companies · its own article →
Open-source vector databases designed to run on your own infrastructure, storing and retrieving embeddings. Machine learning engineers, search teams, and application developers use them to build semantic search, recommendation, and RAG systems without relying on managed cloud services.
Products and companies: sentence transformers, jina ai, nomic, baai bge, ollama.
Papers, last 30 days:- Factorized MLLM Embeddings for Composed Image Retrieval 2026-11-03
- From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings 2026-10-30
- Near-Zero Token Embeddings Silently Stall Training in Gated Sequence Models 2026-11-03
- Erasing the Wrong Thing: Conditional Attribute Leakage and Concept Erasure in Shared Foundation-Model Embeddings 2026-11-19
- DiLE: Discrimination-Aware Latent-Space Learning for Universal Multimodal Embeddings 2026-11-19
vector db management and tooling4 products and companies
Open-source self-hosted vector databases allow organizations to store, index, and query high-dimensional vectors on their own infrastructure without vendor lock-in. Data engineers, ML teams, and enterprises use these to build RAG systems, semantic search, and similarity matching without cloud dependencies.
Products and companies: attu, vectordbbench, airbyte, unstructured.
See also
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.