LanceDB

Embedded multimodal vector DB

Free tier + paidSearch, vector & RAGlancedb.com

What it is

An embedded vector database built on the Lance columnar format — no server process, data sits as files on local disk or in S3. Does vector similarity, full-text search and SQL filtering over the same table, and stores raw bytes, images and video alongside embeddings. Python, TypeScript and Rust SDKs.

Why it earns a slot

Think SQLite for vectors: pip install lancedb, point it at a directory, done. Zero-copy automatic versioning lets you time-travel an index, and the same code scales to the cloud tier.

Know before you commit

Embedded mode has no multi-writer coordination — one writer at a time, or move to the managed tier. Cloud per-unit rates are behind a calculator rather than published.

Getting started

pip install lancedb

Field notes

0 from the community

Loading notes…

Field check

Unverified

Pricing snapshot

OSS free (Apache 2.0), embedded, no server. LanceDB Cloud is usage-based across writes, queries and storage with $100 in free credits on the first month. Enterprise is custom.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate LanceDB (https://lancedb.com) for this project, then use it only if it fits what we are already building.
Context: Embedded multimodal vector DB. An embedded vector database built on the Lance columnar format — no server process, data sits as files on local disk or in S3. Does vector similarity, full-text search and SQL filtering over the same table, and stores raw bytes, images and video alongside embeddings. Python, TypeScript and Rust SDKs.
Reviewer notes (general, not written for this codebase): Think SQLite for vectors: pip install lancedb, point it at a directory, done. Zero-copy automatic versioning lets you time-travel an index, and the same code scales to the cloud tier.
Watch out for: Embedded mode has no multi-writer coordination — one writer at a time, or move to the managed tier. Cloud per-unit rates are behind a calculator rather than published.
Pricing: OSS free (Apache 2.0), embedded, no server. LanceDB Cloud is usage-based across writes, queries and storage with $100 in free credits on the first month. Enterprise is custom.
Setup: pip install lancedb
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/lancedb

Neighbourhood

How LanceDB sits against the rest of the atlas — swaps, companions and the tools builders actually save alongside it.

Instead of thisFuse.js MiniSearch Pagefind Algolia Brave Search API Chroma Cloudflare Vectorize Elastic Cloud Exa

Named in the wiringTypeScript

Also in Search, vector & RAG

Algolia

algolia.com

Hosted keyword search API

Free tier + paidSearch, vector & RAG

Free: 10K search requests/mo + 50K records. Grow: $0.50 per 1K searches + $0.40 per 1K records (10K searches / 100K records included). Grow Plus $1.75 per 1K searches. Elevate with NeuralSearch is custom.

Open dossier

Brave Search API

brave.com

Independent web index search API

PaidSearch, vector & RAG

$5/month in free credits applied automatically; no standing free query allowance. Search $5 per 1K requests at 50 QPS. Answers $4 per 1K requests plus $5 per million input/output tokens at 2 QPS. Enterprise custom.

Open dossier

Chroma

trychroma.com

Embedded vector DB + cloud

Free tier + paidSearch, vector & RAG

OSS free (Apache 2.0). Chroma Cloud Starter: $0/mo base with $5 free credits, then usage. Team $250/mo + usage with $100 credits. Rates: $2.50 per GiB written, $0.33 per GiB-month stored, $0.0075 per TiB queried, $0.09 per GiB returned.

Open dossier

Cloudflare Vectorize

developers.cloudflare.com

Serverless vector DB on Workers

Free tier + paidSearch, vector & RAG

Workers Free: 5M stored vector dimensions, 30M queried dimensions/mo. Workers Paid ($5/mo): 10M stored and 50M queried included, then $0.05 per 100M stored dimensions and $0.01 per million queried dimensions.

Open dossier