LanceDB

Vector storesApache-2.0

LanceDB is a retrieval library built on the Lance data format that runs inside an application process, with a separate Enterprise service for production workloads. The README lists Python, TypeScript and Rust SDKs, and the documentation includes a REST API reference for the Enterprise service. The quickstart connects to a local directory with a single call and searches a table with a query vector. The documentation names integrations with OpenAI, Cohere, LangChain, LlamaIndex, DuckDB and Pydantic.

Pinout

  • MCP server: not checked yet
  • HTTP API: supported, verified
  • command line: not checked yet
  • Python SDK: supported, verified
  • TypeScript SDK: supported, verified
  • OpenAPI description: not checked yet
Where each pin comes from
InterfaceStatusSource we readRead on
MCP serverNot checked yet——
HTTP APISupported, verifiedREST API Reference
Command lineNot checked yet——
Python SDKSupported, verifiedGitHub README, SDK list
TypeScript SDKSupported, verifiedGitHub README, SDK list
OpenAPI descriptionNot checked yet——

Facts

Facts about LanceDB
LicenseApache-2.0. GitHub repository, About sidebar, read .
Latest GitHub releasev0.41.0. GitHub releases, latest, read .
OfferingsEmbedded open-source library, and Enterprise, a distributed service with managed infrastructure and private deployment. Documentation home, read .
SDKsPython, TypeScript and Rust. GitHub repository README, read .
REST APIREST API Reference exists; endpoints use a host set by the Enterprise administrator. REST API Reference, read .
Integrations namedOpenAI, Cohere, HuggingFace, LangChain, LlamaIndex, Kiln, DuckDB, Pydantic, dlt. Integrations, read .
Last commit. GitHub API, latest commit on the default branch of lancedb/lancedb, read .
FrameworksOpenAI (Integrations, read 2026-11-16); Cohere (Integrations, read 2026-11-16); HuggingFace (Integrations, read 2026-11-16); LangChain (Integrations, read 2026-11-16); LlamaIndex (Integrations, read 2026-11-16); DuckDB (Integrations, read 2026-11-16); Pydantic (Integrations, read 2026-11-16).

Call example

import lancedb

uri = "ex_lancedb"
db = lancedb.connect(uri)

Strengths

  • Runs in the application process with a local directory as the database.
  • Documentation names nine integrations.

Alternatives to LanceDB

All vector stores tools for agents
  1. Open-source vector database with Lite, Standalone and Kubernetes deployments.

    Vector stores
  2. Rust vector database with REST, gRPC, SDKs and an MCP server.

    Vector stores
  3. Open-source embedding database with Python and TypeScript clients and a CLI.

    Vector stores
  4. Postgres extension that stores vectors and runs nearest-neighbor queries in SQL.

    Vector stores

Last check: . Method: public repository and docs read automatically, page and day written down. Next check due within 90 days. How we check

Is this your tool? Write to hello@agent-tools.directory from an address on its domain to correct a pin or a fact.