Skip to content

Vector databases

Peak · emerged February 2017 · high April 2026 · +7% on the month before · 4 mentions on Trending in 14 days

Databases that store embeddings and find the nearest ones fast, the retrieval layer under RAG and semantic search. Named by Johnson, Douze and Jegou, Facebook AI Research: Billion-scale similarity search with GPUs (FAISS) (Feb 28, 2017). Also called Vector search, Vector store, Embeddings database, pgvector.

Index 0 to 100, monthly
03569201820192020202120222023202420252026Origin

Signals

SignalReads as
Hacker News stories, last 12 months202 stories, +17% on the 12 months beforeAdoption
arXiv papers, last 12 months362 papers, +61% on the 12 months beforeAdoption
Wikipedia views, August 20267,297, -26% on a year beforeDecline
Product releases naming it167 since Sep 1, 2025Adoption
GitHub repositories12,056Adoption

Companies

Releases

167 releases since Sep 1, 2025
Name
Mem0 Python SDK (v2.2.0)Mem0 · Sep 23, 2026 2 days ago
Amazon Bedrock Managed Knowledge Base now supports Salesforce and Zendesk as native data source connectorsAWS · Sep 23, 2026 2 days ago
Select AI for JavaOracle · Sep 22, 2026 3 days ago
You can now use the AlloyDB Columnar Engine as a read-optimized, in-memory cache for HNSW vector indexesGoogle Cloud · Sep 21, 2026 4 days ago
Temporal 1.32.0Temporal · Sep 19, 2026 6 days ago
What's new in SigmaSigma Computing · Sep 18, 2026 7 days ago
Manage Neki extensions with Terraform and the CLIPlanetScale · Sep 18, 2026 7 days ago
Promptfoo 0.123.1Promptfoo · Sep 18, 2026 7 days ago

GitHub projects

12,056 repositories
NameStars
milvus-io/milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search · Sep 16, 2019 7 years ago46,248
qdrant/qdrantQdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud · May 30, 2020 6 years ago34,798
weaviate/weaviateWeaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structur · Mar 30, 2016 10 years ago16,842
alibaba/zvecA lightweight, lightning-fast, in-process vector database · Dec 5, 2025 9 months ago16,002
rocketride-org/rocketride-serverHigh-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model pr · Feb 11, 2026 7 months ago11,048
objectbox/objectbox-javaDatabase for Android and JVM - first and fast, lightweight on-device vector database · Jan 24, 2017 9 years ago4,624
MovementStage
RAGRetrieval-augmented generation: a model answers from documents fetched for the question instead of from memory alone.Plateau
AI searchSearch that answers with a written summary and citations instead of ten blue links, and the deep research agents that followed.Peak

History

DateWhat changed
Sep 24, 2026Tracking started: emerged February 2017, peak, 4 other names recorded

Sources: Curve: Hacker News story titles, Wikipedia pageviews and arXiv papers by month, refreshed Sep 24, 2026. Related entities from the fru.dev sites' public APIs, matched by name. How stages work.

Trending terms by email

Monday mornings: the week's top trending terms in data, tech and AI.

Double opt-in. Unsubscribe any time.