Weaviate

Platform

Open-source vector database with hybrid search and built-in vectorizers

Price: Free tier, then paid
Access: API key (optional when self-hosted)

About

Vector database that stores objects with their embeddings and runs vector, keyword (BM25) and hybrid search. Self-host the BSD-3-Clause engine with Docker or Kubernetes, or use Weaviate Cloud, whose free plan holds 100,000 objects.

What you can do with it

Search documents by meaning, by keywords or both in one query
Retrieve context and generate an answer with an LLM in one RAG call
Let Claude or Cursor query your collections through the built-in MCP server

Get started

Start Weaviate with Docker or create a free Weaviate Cloud cluster
Create a collection and import objects
Run a vector, keyword or hybrid query

Example

docker run -d -p 8080:8080 -p 50051:50051 cr.weaviate.io/semitechnologies/weaviate:1.39.5
curl http://localhost:8080/v1/.well-known/ready
curl -X POST http://localhost:8080/v1/schema \
  -H 'Content-Type: application/json' \
  -d '{"class": "Movie"}'

Details

Hosting: Hosted service, Self-hosted
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript, Go, Java, C#
MCP server: Remote