LanceDB
Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.
At a glance
- Type
- Embedded Arrow-columnar vector DB
- Tier
- T1
- Section
- Vector-database infrastructure
- Created
- 2023-02
- Latest release
- python-v0.31.0-… 2026-04-29
- License
- Apache-2.0
- GitHub
- 10.2k★ +200/mo HTML
- Pricing
- Free + paid
- Funding
- $38M total Series A · 2025-06
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
Built on Lance columnar format — gives you vector search + analytical SQL on the same data without ETL between systems.
Cons
Newer ecosystem; fewer integrations than Pinecone / Weaviate; Lance format is non-standard so portability requires conversion.
Claims & capabilities
Lance format v2.2 cuts storage 50%+; up to 68x faster blob reads vs Parquet; production architecture targets 25ms vector search latency, 50ms with metadata filtering, thousands of QPS; benchmarks on 1M 960-dim GIST: <20ms queries, recall@1 ~0.90 in 3ms via IVF + PQ; LanceDB Cloud (serverless, usage-based) launched public beta 2025
Technical surface
- API surface
- REST (cloud), SDK: Python, JS/TS, Rust
- Backend storage
- custom (Lance columnar format on object storage)
- Deployment
- Both
- Embedding model
- multiple supported
- Multi-tenancy
- Logical namespace per dataset; embedded library or LanceDB Cloud (single-tenant available)
- 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.
Compare LanceDB with…
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).
- 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).
- Milvus T1
Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).
Related systems
Referenced by (2)
- Agno (Phidata) Memory integrates with — Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- Cognee depends on at runtime — adjacent-infrastructure cell: BYO LLM; bundles Kuzu/Neo4j for graph + LanceDB for vectors