
Missed a lecture? This AI agent at Bar-Ilan University helps students catch up
The post Missed a lecture? This AI agent at Bar-Ilan University helps students catch up appeared first on Source.
Stay updated with the latest developments in Artificial Intelligence

The post Missed a lecture? This AI agent at Bar-Ilan University helps students catch up appeared first on Source.
Issue #4 of The State of Serene: faster search on every core and from a cold cache, regex and fuzzy search that always answer, text analyzers as expressions, HNSW, the docs inside the binary, OpenTelemetry ingestion, faster time histograms, MATCH_RECOGNIZE, spatial and AI functions.
SereneDB launches Krummelanke, its first production-ready release, combining full-text search and analytics in one open-source, Postgres-compatible engine for AI agents.
We ran 92 search and analytics queries over 100M, 1B and 10B OpenTelemetry logs against ClickHouse 26.8 with its new text index and SereneDB, all on a single instance.
We ran 92 search and analytics queries over 100M and 1B OpenTelemetry logs against Elasticsearch 9.5, its new columnar index mode, OpenSearch, CrateDB and SereneDB.
We ran 92 search and analytics queries over 100M and 1B OpenTelemetry logs against vanilla Postgres, ParadeDB with pg_search, TigerData with pg_textsearch and SereneDB.
SereneDB has built a VectorStore integration package for LangChain, pairing flexible AI orchestration with the analytical power of a full-featured database.
Issue #3 of The State of Serene: sloppy phrase search, Lucene query syntax, REINDEX and search over Iceberg, per-node score and merge control, Azure blob storage and a faster postings read path.
Serene WYL turns a finished Dota 2 match into a layered review: an overview, deep analysis, an interactive replay and recommendations based on real games.
Build a SereneDB full-text index over tables in Postgres or ClickHouse, choose which columns stay local and query the results through SQL.
Six years ago, when we first shipped fuzzy search (yes, without agents!), we wrote up the two algorithms
Serene Docs Search is a self-hosted, Apache 2.0-licensed documentation search stack with BM25, optional hybrid search, Ask AI and MCP, powered by SereneDB.
Issue #2 of The State of Serene: term-dictionary facets, IVF vector search, online CREATE INDEX, PostgreSQL RBAC, a ClickHouse connector and the SearchBench numbers against ArangoDB.
One year after we started SereneDB we ran 92 search and analytics queries over 1B OpenTelemetry logs and put the numbers next to ArangoDB to see how far we have come.
Issue #1 of The State of Serene: what SereneDB is — lakehouse search and analytics for your agents — what it does today, and everything we shipped in June 2026.
Building a code-search system over 14 GB of programming solutions in a data lake — searching Parquet in place, without moving the data.
Why SQL is the right language for Search-OLAP: BM25 scores and vector distances belong in the same query plan as your joins and aggregations.
Keep embeddings next to your data: how SereneDB runs vector similarity and hybrid search and manages embeddings under one index, with no separate vector database to sync.
Three demos run the same SQL — Elasticsearch-grade ranked search plus relational analytics — over remote Parquet, local files and a native SereneDB table, without changing the query.
Showing 18 of 20 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news from SereneDB Blog
Join 15,000+ AI enthusiasts