Weaviate Blog the company blog of Weaviate: latest posts and feed
Weaviate · Company blog · 3.9 a month · last post Oct 22, 2026 · Active
Posts
24 on file since Apr 23, 2026SecurityOct 22 2d2 days agoHow Weaviate responded to the eMudhra certificate compromiseWeaviate patched its entire customer estate and infrastructure platform in under 17 hours to mitigate the risk of eight leaked certificates from the eMudhra certificate authority.SecurityOct 15 9d9 days agoWeaviate security release - Medium severity fix for a cross-collection vector disclosure in nearObject (CVE pending assignment)Weaviate v1.39.3 fixes a medium-severity authorization issue in the nearObject GraphQL operator.ResearchOct 14 10d10 days agoPathSeer: Adaptive Filtered Vector SearchWeaviate 1.40 adds PathSeer, a third HNSW filter strategy from a SIGMOD 2026 paper, contributed by the paper's first author. How it works, and how it compares to sweeping and ACORN.AI and agentsOct 8 2w2 weeks agoPersistent memory for Claude Code with Weaviate EngramThe Engram plugin gives Claude Code persistent, long-term memory, so it remembers what you've done and brings it back when it matters.SecurityOct 1 3w3 weeks agoWeaviate security release - High severity fix for credential disclosure in the Google modulesWeaviate v1.39.3 fixes a high-severity credential disclosure issue in the Google modules.AI and agentsSep 22 4w4 weeks agoAgent Memory with Engram: A Practical GuideLearn how to use Engram effectively, from writing topic descriptions that control extraction to choosing bounded topics and scopes, selecting a retrieval mode, and placing memories in your prompt without hurting prompt-cache efficiency.Reliability and performanceSep 17 5w5 weeks ago4-bit Rotational Quantization4-bit Rotational Quantization in Weaviate 1.39: the SIMD performance work, a centered tier, scaling analysis and a TurboQuant comparison.AI and agentsSep 9 6w6 weeks agoHFresh: Memory-Efficient Vector SearchHFresh is Weaviate's disk-based vector index for memory-efficient vector search, combining low heap usage with incremental background maintenance.Product and companySep 8 6w6 weeks agoBuilding Foundry Part 3: From archive to creative searchPart 3: We turn a messy creative archive into a searchable library using a manifest, Weaviate, and hybrid search.AI and agentsSep 1 7w7 weeks agoHow to extract meaning from charts and tables in PDFsPDFs full of charts and tables are notoriously hard to put through a traditional RAG pipeline. In this post, we show how late-interaction multi-vector retrieval lets you search PDFs by what the page looks like: no OCR, no chunking, no text...Developer toolsAug 27 8w8 weeks agoWeaviate 1.39 ReleaseWeaviate 1.39 promotes the Boost API and MMR diversity selection to GA, previews 4-bit Rotational Quantization, and ships an experimental Search REST API.Product and companyAug 13 2mo2 months agoBuilding Foundry Part 2: Where creative workflows breakPart 2: Why folders, tags, and keyword search break down in real creative workflows and what retrieval needs to do instead.AI and agentsAug 11 2mo2 months agoScaling Test-Time Compute in Search ModeIntroducing medium, high, and ultrahigh effort tiers to the Query Agent's Search Mode.Product and companyJul 30 2mo2 months agoBuilding Foundry: AI isn’t replacing creativity, it’s removing frictionWhy AI won’t replace creatives, and how it can remove friction from messy workflows, lost files, and creative processes.DatabasesJul 21 3mo3 months agoQuery Profiling: See Where a Slow Query Spends Its TimeWhen a Weaviate query is slow, the first question is where the time went. Query profiling returns a per-stage, per-shard timing breakdown, making query performance issues visible.AI and agentsJun 25 4mo4 months agoWeaviate 1.38 ReleaseThis 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 a single scheduler (on by default), and adds two previews: the Boost API and...Reliability and performanceJun 18 4mo4 months agoImport & Vectorize Data with Weaviate at ScaleServer-side batching, retries, the blobHash data type, and multimodal ingestion, what to use when, with code.InfrastructureJun 17 4mo4 months agoWeaviate Cloud is now free to startWeaviate Cloud is now free to start across the entire product suite.Product and companyJun 3 4mo4 months agoEngram is now Generally AvailableEngram, Weaviate's managed memory and context service for agentic applications, is now generally available.InfrastructureMay 28 4mo4 months agoLeveling up Weaviate Cloud security: Expanding role-based access control for Cloud consoleWeaviate Cloud now supports more granular role-based access control with new Editor and Viewer roles for improved security and organizational management.AI and agentsMay 21 5mo5 months agoBuild a Coding Assistant with Weaviate MCP: RAG over Code & DocsUse Weaviate's built-in MCP server to give Claude Code, Cursor, and VS Code hybrid search over your codebase and docs. No glue code.Product and companyMay 14 5mo5 months agoText Analysis for Hybrid Search: Tokenization, Stopwords & Accent FoldingTokenization makes or breaks hybrid search. See how Weaviate's accent folding, custom stopwords, and /v1/tokenize endpoint power multilingual BM25.AI and agentsMay 6 5mo5 months agoYour LLM Is Only as Good as What It RetrievesA Researcher's Perspective on Retrieval Quality in RAG SystemsAI and agentsApr 23 6mo6 months agoWeaviate 1.37 ReleaseThis release introduces the built-in MCP Server, Extensible Tokenizers, Diversity Search (MMR), and Query Profiling as previews, along with Incremental Backups, Gemini audio support for multi2vec-google, and the new BlobHash property type. About this blog
Weaviate's own blog on weaviate.io, found by the daily check.
Posts per week, last 26 weeks
3.9 a month over the last six months (or since the feed's oldest post)
History
Listed on Blogs Oct 7, 2026. No changes to its feed, status or cadence since.
Blogsby Ibis