LanceDB

https://lancedb.com/

Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.

Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 81 cited facts, 8 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
Created
2023-02 repo fix
Latest release
v0.40.0 (2026-10-07) registry fix
License
Apache-2.0 repo fix
Freshness
2026-10-26 fix
Layer
model-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid repo fix
Platform vs product
platform repo fix
Accelerator
yc-w22 third-party fix
Protocols
mcp-server repo fix
Compliance
gdpr, hipaa, soc2-type2 vendor fix

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 (self-hosted + managed cloud) — embedded OSS library; LanceDB Enterprise as Managed or BYOC
Embedding model
multiple supported
Multi-tenancy
Logical namespace per dataset; embedded library or LanceDB Cloud (single-tenant available)
MCP
yes — official reference server lancedb/lancedb-mcp-server (basic, 3 tools)
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.

  • Chroma T1

    Limited native hybrid (users build RRF custom). Fast Rust core (v2.5). Acquired by Replit (definitive agreement announced 2026-10-23); Chroma Cloud is winding down (writes disabled 2026-11-22, reads disabled 2026-12-22) while open-source ChromaDB continues under Apache-2.0.

  • 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.

  • Weaviate T1

    Hybrid Search 2.0 with learned ranking. BM25 + vector in unified index.

  • Milvus T1

    Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).

  • Pinecone T1

    Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .

Sources (80 cited facts, 8 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-26
    • Latest release “python-v0.31.0-… 2026-04-29” → “v0.40.0 (2026-10-07)” source
    • Pricing “Free + paid” → “free (OSS); LanceDB Enterprise/Cloud pricing via sales (no public price list)” source
    • Deployment “Both” → “Both (self-hosted + managed cloud) — embedded OSS library; LanceDB Enterprise as Managed or BYOC” source
    • MCP support first recorded as “yes — official reference server lancedb/lancedb-mcp-server (basic, 3 tools)” source
    #258

Related systems

References (11)

  • Cohere Embed integrates with — LanceDB's docs have a Cohere Embed integration page. (verified 2026-10-29)
  • Genkit integrates with — LanceDB's docs have a Genkit integration page. (verified 2026-10-29)
  • Google Gemini 3 family integrates with — LanceDB's docs have a Google Gemini 3 family integration page. (verified 2026-10-29)
  • Jina AI Embeddings integrates with — LanceDB's docs have a Jina AI Embeddings integration page. (verified 2026-10-29)
  • LangChain (framework) integrates with — LanceDB's docs have a LangChain (framework) integration page. (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — LanceDB's docs have a LlamaIndex (framework) integration page. (verified 2026-10-29)
  • OpenAI Embeddings integrates with — LanceDB's docs have a OpenAI Embeddings integration page. (verified 2026-10-29)
  • OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with — LanceDB's docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
  • Phidata (now Agno) integrates with — LanceDB's docs have a Phidata integration page. (verified 2026-10-29)
  • Sentence Transformers integrates with — LanceDB's docs have a Sentence Transformers integration page. (verified 2026-10-29)
  • Voyage AI (MongoDB) integrates with — LanceDB's docs have a Voyage AI (MongoDB) integration page. (verified 2026-10-29)

Referenced by (8)

  • 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
  • CrewAI Memory integrates with — CrewAI memory docs say memory is stored in LanceDB by default. (verified 2026-10-29)
  • Haystack (framework) integrates with — Haystack integrations directory has a LanceDB Haystack integration page ("A DocumentStore backed by LanceDB"). (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — LlamaIndex has an official vector store integration package llama-index-vector-stores-lancedb in its repo. (verified 2026-10-29)
  • Mastra integrates with — Mastra repo ships the @mastra/lance (LanceDB) store package. (verified 2026-10-29)
  • OpenLLMetry (Traceloop) integrates with — OpenLLMetry's What's Supported page lists LanceDB as instrumented out of the box. (verified 2026-10-29)
  • Phidata (now Agno) integrates with — Agno ships a lancedb vector DB integration module (agno.vectordb.lancedb). (verified 2026-10-29)