A developer working on the Lakekeeper catalog built a runnable example extending zero trust to agent memory, in which two agents keep private memory in a single catalog, propose skills they cannot pub…
Hugging Face released funes, a durable memory layer for coding agents that indexes and retrieves session traces locally, supporting Claude Code, Codex, pi, and Hermes. The tool, available as a single …
Milvus 3.0, released July 31, introduces a lake-native architecture that allows vector search directly over data in object storage without copying, reducing I/O per point read from 9.4 MB to 0.07 MB (…
Pond, a new open-source tool introduced on Hacker News, lets users archive AI agent sessions into their own S3 bucket or local directory without running a database, using in-process Lance for storage …
Milvus 3.0.0, released by the Milvus project on July 29, 2026, extends the open-source vector database with lake-native retrieval, enabling indexing and search over data in open formats like Parquet, …
Zilliz released Milvus 3.0, introducing a lake-native path for indexing vector data in object storage and open table formats such as Parquet, Lance, Iceberg, and Vortex, enabling teams to search lake-…
Zilliz has launched Milvus 3.0, an update to its open-source vector database that adds lake-native data access and a more expressive retrieval engine for production AI applications. The update enables…
A developer at Dremio details the renaissance in columnar file formats driven by AI workloads and hardware evolution. The analysis covers how Parquet's assumptions are breaking under modern demands, a…
Smolbren, a new CLI tool, turns Markdown vaults into local, queryable knowledge graphs with full-text search, using frontmatter to discover ontology and supporting Cypher queries and BM25 search. Desi…
ModernRelay launched Omnigraph, an open-source graph engine designed for multi-agent coordination and context assembly, featuring Git-style branching, multimodal retrieval, and object-storage-native a…
DuckDB has integrated vector and hybrid search capabilities with the Lance lakehouse format, enabling AI workloads directly from SQL queries. SQLite addressed a security vulnerability with a fix for C…
ByteDance released Lance, an open-source multimodal AI model with 3 billion active parameters that natively handles image generation, video generation, editing, and visual reasoning within a single fr…