What Weaviate is
Weaviate is an open-source AI vector database for storing, indexing, and searching high-dimensional vectors. It is intended as a foundation for search, retrieval-augmented generation (RAG), and agents. Its hybrid search combines vector retrieval with BM25 keyword search, alongside semantic and keyword search. Other capabilities include advanced filtering, vectorizer modules, configurable backups, native multi-tenancy, vector-index compression, and tenant isolation. Weaviate can run as a hosted service or as a self-managed instance locally or with a cloud provider; Docker and Kubernetes are deployment options. Integrations include AWS, Google Cloud, Azure, OpenAI, Anthropic, Cohere, Hugging Face, and Ollama. Weaviate Cloud encrypts data in transit and at rest, supports role-based access controls, and provides automated daily backups. The Free plan includes limits of 100,000 objects, one collection, and up to three tenants, and excludes backups and high-availability replication. Flex starts at $45 a month, while Premium costs $400 a month. Windows use is possible through containers such as Docker or WSL, but native Windows support is not offered.
Who it suits
It suits developers building search, RAG, or agent infrastructure, from startups and scale-ups to enterprises. Teams can choose hosted or self-managed deployment, while Windows users need to use containers such as Docker or WSL.
Good to know, and what to watch
- Hybrid vector and BM25 keyword search
- Supports hosted and self-managed deployments
- Integrations include major cloud and model providers
- Cloud service includes encryption and role-based access controls
- SDKs available for Python, TypeScript/JavaScript, Go, Java, and C#
- Free plan is limited to 100,000 objects and one collection
- Free plan has no backups or high-availability replication
- Native Windows support is not offered
Plans
Every plan and priceFree
Flex
Premium
Free plan
Getting started
- Visit the Weaviate website
- Choose hosted service or self-managed deployment
- Deploy locally or with a cloud provider using Docker or Kubernetes
- Select the Free, Flex, or Premium plan
- Connect through a listed SDK or integration
Limits to check
The Free plan allows 100,000 objects, one collection, up to three tenants, 1 GB memory, 10 GB disk, 2,000 embedding requests per day, and 1,000 Query Agent requests per month. It does not include backups or high-availability replication.
The verdict
Weaviate offers vector storage and search with hybrid retrieval, filtering, and multiple deployment options. Check the Free plan’s object and collection limits, and note that backups and high-availability replication are not included at that tier.
Questions people ask
Is Weaviate open source?
Yes. Weaviate is described as an open-source AI vector database.
What does the Free plan cost?
The Free plan costs nothing and is billed forever.
What are the paid prices?
Flex starts at $45 a month with pay-as-you-go monthly billing. Premium costs $400 a month with a prepaid contract.
Can it run on Windows?
Windows use is possible through containers such as Docker or WSL. Native Windows support is not offered.
Which integrations are available?
Named integrations include AWS, Google Cloud, Azure, OpenAI, Anthropic, Cohere, Hugging Face, and Ollama.
What the maker publishes
- Company details
- The company page describes Weaviate as a global remote-first startup but does not state its headquarters or founding year. source
- Compliance
- The pricing page states that Weaviate Cloud is SOC 2 audited and that Enterprise Cloud on AWS is HIPAA compliant. source
- Deployment
- Weaviate can run as a hosted service or a self-managed instance locally or with a cloud provider; deployment options include Docker and Kubernetes. source
- Founded
- 2019 source
- Free plan
- Yes source
- Integrations
- The integration ecosystem lists cloud and model integrations including AWS, Google Cloud, Azure, OpenAI, Anthropic, Cohere, Hugging Face, and Ollama. source
- Intended users
- The company describes Weaviate as infrastructure for developers and says its deployments serve startups, scale-ups, and enterprises. source
- Other features
- Listed features include advanced filtering, vectorizer modules, configurable backups, native multi-tenancy, vector-index compression, and tenant isolation. source
- Plan limits
- The Free plan has 100,000 objects, one collection, and up to three tenants; the pricing comparison lists no backups or high-availability replication for Free. source
- Product
- Weaviate is an open-source AI vector database for storing, indexing, and searching high-dimensional vectors, used as a foundation for search, RAG, and agents. source
- RAG
- The product page describes out-of-the-box RAG that lets users interact securely with proprietary data through machine-learning models. source
- Search
- The database supports hybrid search that combines vector and BM25 keyword search, along with semantic and keyword search. source
- Security
- The security page states that Weaviate Cloud encrypts data in transit and at rest, supports role-based access controls, and provides automated daily backups. source
- Paid from
- 45 source
- Support
- Free includes Basic Support; Flex lists Standard Support with next-business-day Sev 1 response, while Premium lists enterprise support as fast as 1-hour Sev 1. source
- Windows support
- Weaviate documentation says Windows use is possible via containers such as Docker or WSL, but native Windows support is not offered. source
Checked against the maker's pages on 30 Sept 2026.