LanceDB review

Q: How do I install LanceDB?

Run npm install @lancedb/lancedb. It needs Node.js >= 22.

LanceDB is an open-source embedded retrieval library and multimodal lakehouse for vector, full-text and SQL search over AI data.

Updated Nov 1, 2026. Review written Oct 25, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

LanceDB is an embedded retrieval library and multimodal lakehouse built on the Lance columnar format. LanceDB is for AI teams that want search, feature engineering and training data in one versioned table. LanceDB OSS runs locally or in your cloud, and LanceDB Enterprise covers production scale.

11.8kGitHub stars
+60new stars, week of Oct 25
~2.5Mdownloads a week, +4% vs 4-week avg
#23in RAG, data and memory this week

LanceDB at a glance

Category: RAG, data and memory
Maintained by: LanceDB (organization, @lancedb on GitHub)
License: Apache 2.0
Language: Rust, Python, HTML
Repository: github.com/lancedb/lancedb
Website: lancedb.com/docs
npm package: @lancedb/lancedb 0.40.0
PyPI package: lancedb 0.40.0
Latest release: v0.41.0-beta.14 on GitHub, Oct 25, 2026
First published: Feb 28, 2023

What LanceDB does

LanceDB supports vector similarity search, full-text search and SQL over stored data.
LanceDB stores, queries and filters vectors, metadata and multimodal data such as text, images, videos and point clouds.
LanceDB versions data automatically, so you can manage data versions without extra infrastructure.
LanceDB can use GPUs to build vector indexes.
LanceDB feeds training jobs by sampling, shuffling and scanning columns into GPU-ready batches from local or object storage.
LanceDB offers reranking, embeddings, namespaces and feature engineering through Geneva, according to its documentation.
LanceDB integrates with LangChain, LlamaIndex, Apache Arrow, Pandas, Polars and DuckDB.

How it works

LanceDB OSS is an embedded library that runs locally or in your cloud. You call it from Python, TypeScript or Rust SDKs, or through a REST API. Data is stored in the Lance columnar format on local storage or object storage. LanceDB Enterprise adds production-scale search without servers to manage.

How to install and start using LanceDB

From npm

npm install @lancedb/lancedb

Requirements

Python 3.10 or later for the lancedb Python package.
Node.js 22 or later for the @lancedb/lancedb npm package.

First steps

Follow the LanceDB Quickstart guide at docs.lancedb.com to set up LanceDB locally.
Choose the LanceDB Python, TypeScript or Rust SDK, or use the REST API.

Who LanceDB is for

Developers building semantic, image or multimodal search into AI applications.
ML teams that need one versioned table for curation, features, retrieval and training data.
Python and JavaScript developers who want an embedded vector database without running a server.

Limitations to know

LanceDB OSS targets local and regular-scale workflows. The docs position LanceDB Enterprise for larger-scale needs.
Recent LanceDB pre-releases include breaking changes, such as lazy iterators for table listings and renamed MemWAL APIs.

Is LanceDB growing? Usage data

In the week of Oct 25–31, 2026, LanceDB ranked #220 on the Devtoolwatch Board and #23 in RAG, data and memory, with a momentum score of 42 out of 100. Its main package had about 2.5M downloads that week, +4% against its own 4-week average.

New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).

Show the weekly numbers

New GitHub stars per week for LanceDB
Week of	New stars
Aug 9, 2026	63
Aug 16, 2026	88
Aug 23, 2026	74
Aug 30, 2026	54
Sep 6, 2026	57
Sep 13, 2026	65
Sep 20, 2026	67
Sep 27, 2026	63
Oct 4, 2026	47
Oct 11, 2026	66
Oct 18, 2026	71
Oct 25, 2026	60

On Hacker News

LLMs, RAG, and the missing storage layer for AI, 151 points and 61 comments (Sep 7, 2023)
GPU-Accelerated Indexing in LanceDB, 19 points and 4 comments (Nov 2, 2023)
Show HN: LanceDB is an embedded vector database with a native JavaScript API, 10 points and 1 comments (May 16, 2023)
LanceDB – Developer-friendly, serverless vector database for AI applications, 9 points and 0 comments (Oct 10, 2023)
Lance v2: A columnar container format for modern data (2024), 8 points and 0 comments (Jul 28, 2025)

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

LanceDB alternatives

Other RAG, data and memory tools on the Board in the week of Oct 25–31, 2026, by momentum:

RAG, data and memory ranked by momentum, the week of Oct 25–31, 2026
Rank	Tool	Stars	Downloads/wk
#1	XERJXERJ is a local-first search engine and MCP server for AI agents, packaged as one Rust binary with an Elasticsearch-compatible API.	17.9k	–
#2	MemvidMemvid is a single-file memory layer for AI agents that packages data, embeddings, search indexes, and metadata into one portable .mv2 file.	17.3k	–
#3	LEANNLEANN is a Python vector database and RAG library that recomputes embeddings on demand to keep indexes small on personal devices.	13.7k	–
#4	GraphifyGraphify is an AI coding assistant skill that turns a codebase, with its docs, PDFs, images and videos, into a queryable knowledge graph.	140k	480.7k
#5	MarkItDownMarkItDown is a lightweight Python utility from Microsoft that converts PDFs, Office documents, images, audio and other files to…	193.2k	4.7M
#6	FirecrawlFirecrawl is an API and open source project to search, scrape, crawl, and interact with web pages, returning LLM-ready markdown or JSON…	197.4k	2.9M

All RAG, data and memory tools, ranked

Recent LanceDB releases

v0.41.0-beta.14 (pre-release), Oct 25, 2026
v0.41.0-beta.13 (pre-release), Oct 22, 2026
v0.41.0-beta.12 (pre-release), Oct 21, 2026
v0.41.0-beta.11 (pre-release), Oct 21, 2026
v0.41.0-beta.10 (pre-release), Oct 20, 2026

LanceDB FAQ

Is LanceDB free and open source?

Yes. LanceDB's source code is on GitHub (lancedb/lancedb) under the Apache 2.0 license, so you can use it for free.

How do I install LanceDB?

Run npm install @lancedb/lancedb. It needs Node.js >= 22.

Is LanceDB still maintained?

Yes. The lancedb/lancedb repository was last updated on Oct 25, 2026, and the latest release, v0.41.0-beta.14 on GitHub, came out on Oct 25, 2026.

How popular is LanceDB?

LanceDB has 11.8k GitHub stars as of Nov 1, 2026. It gained 60 new stars in the week of Oct 25–31, 2026, against a 12-week average of 65 a week. Its main package had about 2.5M downloads that week, +4% against its own 4-week average. That made it #23 among RAG, data and memory tools on the Devtoolwatch Board.

LanceDB vs Qdrant: how do they compare?

LanceDB and Qdrant are both tracked by Devtoolwatch as RAG, data and memory tools. LanceDB has 11.8k GitHub stars and Qdrant has 35.4k. In the week of Oct 25–31, 2026, LanceDB's main package had 2.5M downloads and Qdrant's had 4.5M. Qdrant is an open-source vector similarity search engine and vector database written in Rust, with filtering on JSON payloads. Qdrant review.

LanceDB vs pgvector: how do they compare?

LanceDB and pgvector are both tracked by Devtoolwatch as RAG, data and memory tools. LanceDB has 11.8k GitHub stars and pgvector has 23.5k. In the week of Oct 25–31, 2026, LanceDB's main package had 2.5M downloads and pgvector's had 9.4M. pgvector is an open-source Postgres extension for exact and approximate vector similarity search, storing vectors alongside the rest of your data. pgvector review.

What are the best alternatives to LanceDB?

Other RAG, data and memory tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: XERJ (#1), Memvid (#2), LEANN (#3), Graphify (#4), MarkItDown (#5). The alternatives table above has their numbers.

Is LanceDB a vector database?

Yes. LanceDB describes itself as a serverless, low-latency vector database and an embedded retrieval library. LanceDB also supports full-text search and SQL.

Is LanceDB open source?

Yes. LanceDB OSS is open source under the Apache-2.0 license and runs locally or in your cloud. LanceDB Enterprise is a separate platform offering.

Does LanceDB run locally?

Yes. LanceDB OSS is an embedded library that runs on a local machine or in your cloud. It can read data from local storage or object storage.

What is LanceDB used for?

LanceDB is used for vector, full-text and SQL search over multimodal data. Teams also use it for dataset curation, feature engineering and feeding training jobs from one versioned table.

How does LanceDB work?

LanceDB is built on the Lance columnar format. It stores vectors, metadata and raw multimodal data together in versioned tables. You access those tables through Python, TypeScript, Rust or REST interfaces.

Sources

LanceDB README badge

Maintainers can show the tool's weekly Board rank in their README:

[![Devtoolwatch](https://index.devtoolwatch.com/badge/lancedb.svg)](https://index.devtoolwatch.com/tools/lancedb/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].