Weaviate

What it does

Weaviate is a vector database that takes in text, images and other data types, stores them as vectors, and returns search results such as vector, keyword, or hybrid matches. Its homepage describes four capabilities: the vector database itself, a Query Agent that turns natural-language questions into database queries, built-in embedding generation so no separate embedding pipeline is required, and Engram, which is described as creating personalized experiences that adapt to each user over time. Client SDKs are offered for Python, Go, TypeScript and JavaScript, with GraphQL and REST APIs also available.

People typically use Weaviate to build search, retrieval-augmented generation (RAG) and agent applications. Its capabilities include built-in vectorization, multi-tenancy (one cluster can hold many tenants), and a choice of deployment on Weaviate Cloud or self-managed infrastructure. The documentation includes starter guides, Academy courses, and an open-source core repository on GitHub.

Weaviate suits developers building search, retrieval and agent applications who want a managed or self-hosted vector store. The ongoing free cloud plan provides one limited cluster, while Flex has a $45 monthly usage minimum and Premium contracts start from $400 per month. Object storage, vector dimensions, backups and optional AI services affect the bill. Confirm resource limits and model-service allowances before production deployment, and plan how data will be backed up and recovered.

What it can do

• Vector database for storing, indexing and searching high-dimensional vectors
• Query Agent that translates natural-language questions into optimized database queries
• Built-in embedding generation from text, images and other data types
• Hybrid search combining vector and keyword matching
• Multi-tenancy for segmented indexes within a single cluster
• Engram for personalized AI experiences that adapt per user

Works with

• Model provider integrations with AWS, Cohere, Google, Hugging Face and OpenAI, per the Learning Center page

Example workflows

Semantic support-ticket search

Illustrative example. Input: a collection of support tickets loaded into Weaviate. Steps: the developer calls the collection query API with a natural-language phrase such as 'login issues after OS upgrade' using near_text, or uses hybrid search with an alpha weighting. Output: a ranked list of the most relevant tickets.

Vector-only lookup

Illustrative example. Input: a precomputed embedding vector. Steps: the developer calls near_vector with a limit parameter on a collection. Output: the nearest stored objects returned by similarity.

Before you choose

• Free has resource, collection, tenant and AI-service limits.
• Paid database minimums do not mean unlimited embedding or Query Agent use.
• Check backup, region and storage pricing and test restoration before production use.

Listed under

• Coding
• Sandboxes and infrastructure
• Agent memory
• AI memory
• Developers
• Embeddings
• Open source
• RAG

Get started

Sign up for the free cluster through the Weaviate Console.

1. Sign up for Weaviate Cloud via the console at weaviate.io/go/console and create a cluster.
2. Install the Python, Go, TypeScript or JavaScript client, or use the GraphQL or REST API, and connect to your cluster.
3. Create a collection, load your data, and run a search query such as near_text or hybrid.

Free provides one cluster with 100,000 objects, 1 GB memory, 10 GB disk, one collection and three tenants. It includes 2,000 embedding requests/day and 1,000 Query Agent requests/month. Flex has a $45/month usage minimum; Premium contracts start from $400/month. Vector, storage, backup and optional service meters differ. Query Agent paid subscriptions and embedding use can add charges. Self-hosting uses your own infrastructure.

Source: weaviate.io/pricing, checked 29 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.

• The AI database developers love | Weaviate ↗weaviate.io
• Shared Cloud Vector Database | Weaviate ↗weaviate.io
• Vector Database Pricing | Weaviate ↗weaviate.io
• Weaviate Learning Center | Weaviate ↗weaviate.io

Company website

weaviate.io: product, pricing and policy pages

YC directory mirror

Batch and company name

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.