beehiiv
Netlify
Plausible Analytics
Postmark
SendGrid
cogneeMemory for AI Agents in 6 lines of code“Weaviate is amazing! It lets us manage the data at scale when we need and how we need it.”
Vector DatabaseMaker says so · source ↗
Weaviate
Open-source vector database combining vector, hybrid, and keyword search for AI and RAG applications.
Works with AI agents:llms.txtAsk your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗
Weaviate is an open-source database that stores data objects together with their vector embeddings, so the same collection can be searched by meaning, by keyword (BM25), or by both in one hybrid query. It is typically the retrieval store behind RAG, semantic search and agent features.
You define collections with typed properties and add objects to them. If you attach a vectorizer integration (OpenAI, Cohere, Voyage AI, Google, Ollama, Hugging Face and others), Weaviate sends the text to that model and stores the returned embeddings at import and query time; otherwise you supply your own vectors. Generative and reranker integrations let a single query retrieve objects and pass them to an LLM. You reach it over REST, gRPC or GraphQL, with official clients for Python, TypeScript/JavaScript, Go, Java and C#.
Useful for a small team: built-in multi-tenancy that puts each tenant on its own shard; filtered search that applies an allow-list from the inverted index inside the vector search; backups to S3, GCS or Azure Storage, including incremental ones; and role-based access control. You can run it with Docker, on Kubernetes, embedded from Python or JS, or on Weaviate Cloud (shared clusters on AWS or GCP, dedicated ones also on Azure).
Limits: Weaviate favours availability over consistency and has no transactions, so its docs suggest keeping data that needs strict serializability in a primary store. There is no native Windows build. The free cloud cluster allows one collection and 100,000 objects.
Where it fits
How Weaviate itself is built
5 tools, from its own code, website and Product Hunt page.
Who uses it
16 makers' products, each linked to the source that shows it, and 20 open-source projects that declare it in their code.
cogneeMemory for AI Agents in 6 lines of code
CortexLet your AI search all your workspace apps, at once“Lightning fast and personalised support for every query. They've helped us brainstorm some architecture level things.”
Vector DatabaseMaker says so · source ↗
Lamatic.aiLamatic is a platform for building AI agents in a visual editor and deploying them as se…“Helped us scale on serverless infrastructure without worry.”
Vector DatabaseMaker says so · source ↗
DepthAI Product Manager“We use Weaviate as a our vector database. Our main feed feature is powered by the vector embeddings Weaviate generates.”
Vector DatabaseMaker says so · source ↗
Insight7Call Analytics and AI Coaching for Customer Teams“Weaviate gives us fast, semantic search across unstructured call data, crucial for surfacing insights in real time. Its native vector support and scalability made it the best fit for building an AI native platform like Insight7.”
Vector DatabaseMaker says so · source ↗
Quantera.aiMarket intelligence & Equity insights just got 10x faster“To store all our vector embeddings, now a staple for us to build forward. Their automatic 'load balancing' on which vectors are recently used is a game changer for system optimization”
Vector DatabaseMaker says so · source ↗“Unbody is built on top of Weaviate, making Unbody content API run 100% on a vector database. Weaviate modular architecture as well as user-friendly GraphQl API has played a vital role in our product.”
Vector DatabaseMaker says so · source ↗
Zefi.aiTransform the voice of your customers into value.“Weaviate has let us manage our data and has supported us since the very beginning. Best team ever and amazing product”
Vector DatabaseMaker says so · source ↗“We chose Weaviate for its great developer experience and seamless integration with vector search and AI-powered queries. It makes working with embeddings and content indexing much simpler.”
Vector DatabaseMaker says so · source ↗Open source: a project that declares Weaviate as a dependency in its public code — verifiable, but not necessarily a live product.
What makers say
8 makers on why they use Weaviate, in their own words on Product Hunt.
Weaviate gives us fast, semantic search across unstructured call data, crucial for surfacing insights in real time. Its native vector support and scalability made it the best fit for building an AI native platform like Insight7.
Insight7Sep 2026 ↗Unbody is built on top of Weaviate, making Unbody content API run 100% on a vector database. Weaviate modular architecture as well as user-friendly GraphQl API has played a vital role in our product.
To store all our vector embeddings, now a staple for us to build forward. Their automatic 'load balancing' on which vectors are recently used is a game changer for system optimization
Quantera.aiSep 2026 ↗We use Weaviate as a our vector database. Our main feed feature is powered by the vector embeddings Weaviate generates.
DepthSep 2026 ↗Lightning fast and personalised support for every query. They've helped us brainstorm some architecture level things.
CortexSep 2026 ↗Loved and watch-outs
Themes that recur in makers' words and Hacker News comments, each linked to what it summarises, with how Product Hunt tags its reviews.
Most loved
- Open source and free to run, with good docs and an active, friendly community. HNweaviate.ioPHHN 2
- Scales to production workloads, including multi-tenant setups on its managed cloud. weaviate.ioPHPH 2weaviate.io 2
- Built-in vectorization and a GraphQL API let queries mix semantic search with structured data. PHHNHN 2
- Self-hosted costs stay low even with steady multi-user usage. HNHN 2
Reliability and open issues
Most wanted on GitHub
- Reindex API (Inverted Index)👍 70 · opened Nov 2022 · active Feb 2026
- Possibility to update or/and delete a property👍 60 · opened Mar 2023 · active Apr 2026
- Feature request: Cross-tenant queries👍 27 · opened Sep 2023 · active Apr 2026
- [Proposal] Add [ImageRef] image reference type👍 19 · opened Mar 2023 · active Oct 2025
Alternatives to Weaviate
All alternatives by situation →
Pinecone
Qdrant
pgvector
Chroma
turbopuffer
LanceDB
MongoDB
MilvusQuestions makers ask about Weaviate
Can Weaviate create the embeddings for me?
Yes. With a model provider integration enabled, Weaviate sends an object's text properties to the provider (API-based ones like OpenAI or Cohere, or locally hosted ones like Ollama) and stores the vectors it returns. You can also import your own vectors instead. source ↗
Which languages have official clients?
Python, TypeScript/JavaScript, Go, Java and C#. Anything else can call the REST, gRPC or GraphQL APIs directly, and some community clients exist. source ↗
How do I keep each customer's data separate?
Enable multi-tenancy on the collection. Each tenant is stored on its own shard and its data is not visible to other tenants; you can also let Weaviate create tenants automatically on insert. source ↗
What are the limits of the free cloud cluster?
One free cluster per user, with up to 100,000 objects, one collection and three tenants. It is suspended after 7 days without activity and deleted after 30 days, with a warning email the day before. source ↗
Does Weaviate support transactions or strong consistency?
No. It has no transactions, each operation touches a single object, and a distributed cluster is eventually consistent. For data that needs strict serializability, the docs recommend a separate primary store with Weaviate alongside it. source ↗
Is Weaviate Cloud SOC 2 and HIPAA compliant?
Weaviate Cloud is SOC 2 Type II audited. HIPAA compliance is available only on the dedicated (Enterprise) deployment on AWS. source ↗
How do backups work when I self-host?
The backup feature writes a whole instance or selected collections to S3, GCS or Azure Storage with one command, supports incremental backups, and can restore to a different provider. There is no per-tenant restore; restoring brings back the whole collection. source ↗
Can I run it on Windows?
Only through Docker or WSL. There is no native Windows support, and the docs advise against Embedded Weaviate there. source ↗
Is Weaviate free?
Yes — there is a free tier a small product can run on; paid use starts at $45/mo. source ↗
Is Weaviate open source or self-hostable?
Open source, and you can self-host it. source ↗
Can AI coding agents work with Weaviate?
It serves an llms.txt docs index.
Who uses Weaviate?
16 makers' products we track, each with a source, and 20 open-source projects declare it in their code. source ↗