📰 Weaviate Blog

This release brings the HFresh disk-based vector index and the built-in MCP Server to general availability, rebuilds cluster-wide async replication to run from

Server-side batching, retries, the blobHash data type, and multimodal ingestion — what to use when, with code.

Engram, Weaviate's managed memory and context service for agentic applications, is now generally available.

Weaviate Cloud now supports more granular role-based access control with new Editor and Viewer roles for improved security and organizational management.

Use Weaviate's built-in MCP server to give Claude Code, Cursor, and VS Code hybrid search over your codebase and docs. No glue code.

A Researcher's Perspective on Retrieval Quality in RAG Systems

This release introduces the built-in MCP Server, Extensible Tokenizers, Diversity Search (MMR), and Query Profiling as previews, along with Incremental Backups,

Two weeks of dogfooding Engram, Weaviate's memory product, in daily Claude Code sessions. This surfaced where a dedicated memory product adds value, and the spe

Multimodal embeddings allow AI systems to search and reason across text, images, audio, and video in their native formats. This blog covers the key intuitions b

Use semantic search and RAG in C# with the Weaviate Managed .NET client — attribute-driven schema, type-safe queries, and safe migrations, all in idiomatic .NET

A complete guide on how to secure Weaviate enterprise deployments with OIDC, RBAC, and multi-tenant isolation.

This release introduces HFresh vector index (Preview), and brings Server-side Batching, Object TTL, Async Replication Improvements, Drop Inverted Indices, and B

Learn how we built a production-ready, end-to-end RAG application in just 36 hours using the Query Agent and the new Weaviate Agent Skills library.

Build production-ready agent workflows with a single prompt in Claude Code, Cursor, and GitHub Copilot.

Learn how to secure your Weaviate vector database with API keys, OIDC, and role-based access control (RBAC). Includes practical examples and setup steps.

Memory isn't just a feature for AI applications—it's infrastructure. As agents scale, the limited loop of stateless interactions breaks down, and continuity bec

2025 was a defining year for us at Weaviate. Instead of chasing shiny features, we focused on an overarching goal - upgrading our infrastructure and technology

Why vector databases are here to stay.

The Weaviate C# client is now generally available! This release brings a modern and intuitive API for .NET developers, making it easier than ever to build AI-po

This release introduces Object Time-to-Live (TTL), zstd compression support, flat index RQ quantization, multimodal support with Weaviate Embeddings, runtime co

Context engineering is how AI agents manage LLM memory—selecting, retrieving, and organizing context from short-term and long-term memory to improve reliability

Weaviate recognized by AWS Partners in Benelux as leaders in helping customers drive innovation

The Weaviate Java client v6 is now generally available! This release brings a completely redesigned API that embraces modern Java patterns, simplifies common op

Learn how to use the Dify and Weaviate integration to build RAG applications.