AI Briefing#vector-search
The latest AI and developer news about #vector-search, with the original source and a short summary.
The latest AI and developer news about #vector-search, with the original source and a short summary.
Manticore Search has released version 27.1.5, including authentication features, sharding, conversational search, and vector search performance improvements.
Amazon has unveiled the next-generation **Amazon OpenSearch Serverless**, optimized for building AI agents.
OpenSearch has unveiled agentic search, where AI agents reason beyond simple search, along with cost-efficient tiered storage technology.
pynear 2.3, a high-performance SIMD-accelerated KNN library compatible with scikit-learn, has been released.
A memory system that solves the session-memory problem for AI coding agents has been released.
LLM Wiki v2 grows into an operational knowledge base by adding lifecycle management, graphs, and automation.
GloZ redesigned its search pipeline and indexing for 100,000 resumes using OpenSearch and Bedrock.
The open-source memory layer memv has launched an MCP server, making it available for use in Claude Desktop, Code, and more.
Viewcomms used CESC on Amazon ElastiCache for Valkey to cut Tadak v2 image response times to under 100ms and lower generation costs by 35%.
mind-mem has released a hybrid memory MCP combining BM25+vectors+RRF.
A 3-bit vector search package that runs in browsers and Node.js has been released.
OlmoEarth Studio unveiled a feature to export Earth observation embeddings as COG.
Facebook Groups search quality was improved through hybrid retrieval and automated evaluation.
Cloudflare has unveiled the private beta of **Agent Memory**, which preserves memory across sessions.
Agent memory reveals bottlenecks across search, cost, and memory management alike.
pgvector 0.8.0 in Aurora PostgreSQL significantly boosts the speed and recall of filtered vector search.
Agent memory isn't simply about extending context—it's a problem of structured storage and retrieval.
Netflix built real-time multimodal video search with a Cassandra-Kafka-Elasticsearch pipeline.
Weaviate has unveiled Engram, a vector search-based memory system designed to solve the context-loss problem in LLM sessions.
SK Planet has developed 'Seg Lens', a DMP combining LLM and vector search, to instantly convert marketers' natural language intent into actionable segments.
Embedding quantization techniques are presented as a way to reduce the memory usage and cost of vector search while increasing speed.