Alternatives to pgvector

Open-source vector database for billion-scale AI similarity search.

Open-source distributed SQL database with vector search, ACID transactions, and HTAP for AI agent workloads.

Open-source real-time SQL analytics, full-text search, and vector database for AI.

Zvec: open-source, in-process vector database with sub-millisecond search at billion scale.

Free open-source admin UI for ChromaDB vector database

Open-source, cloud-native data warehouse in Rust unifying analytics, vector search, and full-text search on object storage.

Open-source multimodal lakehouse for AI data curation, feature engineering, search, and training.

Open-source AI search platform unifying vector, text, and ML ranking for scalable applications.

Open-source, serverless vector search built on object storage that claims up to 10x lower cost.

Serverless vector database with hybrid search for GenAI apps, auto-scaled to your workload

Open-source context retrieval layer grounding AI agents in real-time data from your apps and databases.

Distributed transactional document database with vector search for AI agents on FoundationDB.

Fully managed vector database for fast, accurate AI retrieval at scale

Open-source RAG engine with advanced ETL, hybrid search, and visual agent orchestration for enterprise AI.

Open-source AI database with vector search, RAG, and managed agent memory.

Open-source vector database for production-grade AI retrieval at scale, with hybrid search and advanced filtering.

Open-source lakehouse format for multimodal AI with hybrid search.

Open-source content intelligence engine for CPU-only document extraction

Open-source incremental data framework for AI agents, processing only deltas for always-fresh context.

GPU-native serverless PostgreSQL with vector search for AI agents.

Build AI apps with MongoDB Atlas—native vector search, hybrid search, and reranking in one multi-cloud data platform.

Open-source protocol suite for standardizing LLM, vector, graph, and embedding infrastructure.

Open-source PDF-to-vector pipeline for RAG in one command.

Local-first vector database for AI agents, RAG, and edge workloads.

Open-source knowledge-graph RAG that maps entities and communities to answer complex, cross-document questions.

Vespa is a distributed serving engine that unifies vector, text, and ML ranking for AI search at scale.

Fully managed vector lakebase for high-scale AI search, RAG, and recommendations.

In-memory graph database for real-time GraphRAG and AI memory

Open-source CLI that turns 18 source types into AI skills and RAG knowledge for 22 AI platforms.

One universal database engine for AI, replacing 5 separate databases in a single SQL query.