Vector database9 of 5720 tools
9 tools filed under Vector database by what their own homepage shows, ranked by who uses them among those still maintained.
A tag is one of thirty-odd words from a closed list, chosen by the same reader from the same page as the line — never a keyword the vendor supplied.
Ranked by use
Pinecone
pinecone.ioStores and retrieves vector embeddings at scale for retrieval-augmented generation and agent knowledge systems.
SurrealDB
surrealdb.comStores documents, graphs, vectors, and relational data in one engine with built-in agent memory layer.
Zilliz
zilliz.comManages vector data for AI applications with real-time search, discovery, and analytics on a single platform.
Qdrant
qdrant.techStores and searches vectors at scale with metadata filtering, hybrid search, and reranking.
Weaviate
weaviate.ioVector database that stores, indexes, and searches high-dimensional vectors for retrieval-augmented generation and semantic search.
turbopuffer
turbopuffer.comVector and full-text search database built on object storage, scaling to 256TB per index with sub-10ms latency.
YantrikDB
yantrikdb.comPersistent memory database for AI agents that stores and retrieves facts across sessions with conflict detection.
zinfradb
zinfradb.comStores and searches vectors, graphs, and text in a single database binary.
Supermemory MCP
supermemory.aiStores and retrieves learned context for agents using a vector graph database, injecting relevant memories into model prompts in real time.
LLM operationsFrom $19/mo
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one row at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.