turbopuffer
turbopuffer.com- Category
- Developer Tools
- Platform
- web
- Type
- TOOL
- Added
- Jul 30, 2026
About
turbopuffer is a vector and full-text search database built directly on object storage (like S3), offering sub-10ms query latencies while being roughly 10x cheaper than traditional in-memory vector databases. It supports hybrid vector plus BM25 full-text search with metadata filtering, and is used in production by companies like Cursor, Notion, Anthropic, and Linear at scales exceeding 4 trillion documents and 10 million writes per second.
Why it made the leaderboard
If your RAG or search index is growing past the point where a memory-resident vector DB is affordable, turbopuffer stores indexes directly on S3 with SSD caching, cutting storage cost roughly 10x while still hitting sub-10ms p50 on cached namespaces. It also does hybrid BM25 + vector search and metadata filtering natively, so you don't need a separate full-text engine alongside it.
Tags
Media
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.