Turbopuffer
Object-storage-first vector DB. Powers Notion and Cursor. SPFresh indexing; ~10× cost reduction vs. memory-resident peers.
At a glance
- Type
- Object-storage-first vector DB
- Tier
- T1
- Section
- Vector-database infrastructure
- Created
- 2023
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Pay-per-use
- Funding
- Seed+ · 2025-12
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- overwrite
- unit
- chunk
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: low-latency similarity search + scale
Anti-fit: not for relational / graph-heavy queries (vector-first by design)
Pros & cons
Pros
Object-storage-backed vector DB at order-of-magnitude lower cost than peers; excellent for write-once-read-rarely memory.
Cons
Latency is higher than RAM-resident DBs; newer product with limited operational track record.
Claims & capabilities
Production scale: 3.5T+ documents, 10M+ writes/s, 25k+ queries/s; up to 100B vectors at 200ms P99; sub-10ms P50 latency; reports 95% cost reduction switching from traditional vector DBs (object-storage at $0.02/GB vs $0.60/GB); customers include Cursor, Notion, Linear, Anthropic; revenue 10x and headcount 5x in 2024–2025
Technical surface
- API surface
- REST, SDK: Python, TS, Go
- Backend storage
- custom (object-storage native vector engine)
- Deployment
- Hybrid
- Embedding model
- BYO
- Multi-tenancy
- namespace
- MCP
- no first-party MCP adapter published as of 2026-05; community connectors may exist.
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- no first-party OpenTelemetry exporter documented; standard logs/metrics typically available.
Similar systems
Other vector-database infrastructure in the catalog, ranked by inbound references.
- Qdrant T1
Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.
- pgvector T1
Stores embeddings alongside relational + full-text data. HNSW + IVFFlat ANN indexes. Used as agent conversation memory via LangChain + MCP. Foundation of Supabase AI and many self-hosted RAG stacks.
- Pinecone T1
Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .
- Chroma T1
Limited native hybrid (users build RRF custom). Fast Rust core (v2.5).
- LanceDB T1
Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.
- MongoDB Atlas Vector Search T1
Agent memory store for both short-term (document) and long-term (vector). LangGraph checkpointer for stateful agents. Vector search extended to Community Edition (Sept 2025).