Updates and insights from the OpenData projecthttps://www.opendata.dev/en-ushttps://www.opendata.dev/blog/vector-bench/https://www.opendata.dev/blog/vector-bench/We're open-sourcing Vector Bench, the harness we use to measure OpenData Vector's recall, warm/cold query latency, and ingestion throughput. Point it at the built-in ANN datasets or your own data to project performance and cost for your workload.Thu, 04 Jun 2026 00:00:00 GMTvectorbenchmarkssearchslatedbRohan Desaihttps://www.opendata.dev/blog/ingesting-1gbps-logs-to-clickhouse/https://www.opendata.dev/blog/ingesting-1gbps-logs-to-clickhouse/New pipelined producer and consumer clients for OpenData Buffer, plus a ClickHouse integration with batch deduplication, move 1.1 Gbps of logs from an OTel Gateway to ClickHouse via S3 for $180/mo.Fri, 29 May 2026 00:00:00 GMTbufferclickhouseobject-storageotelannouncementApurva Mehtahttps://www.opendata.dev/blog/introducing-vector/https://www.opendata.dev/blog/introducing-vector/An MIT-licensed, stateless vector search engine built on SlateDB that runs anywhere with object storage and serves 100M vectors for roughly $350/mo.Thu, 14 May 2026 00:00:00 GMTvectorslatedbsearchannouncementRohan Desaihttps://www.opendata.dev/blog/faster-timeseries-aggregations/https://www.opendata.dev/blog/faster-timeseries-aggregations/How we reworked OpenData Timeseries' query execution engine to 2x real-world performance by using cache-friendly, tiled columnar execution.Wed, 06 May 2026 00:00:00 GMTtimeseriesperformancequery-engineAlmog Gavrahttps://www.opendata.dev/blog/buffer-ha-pipelines-without-kafka/https://www.opendata.dev/blog/buffer-ha-pipelines-without-kafka/An MIT-licensed buffer that turns object storage into a low-latency queue between producers and consumers, replacing Kafka for telemetry pipelines at a fraction of the cost.Wed, 29 Apr 2026 00:00:00 GMTbufferkafkaobject-storageannouncementBruno Cadonnahttps://www.opendata.dev/blog/introducing-timeseries/https://www.opendata.dev/blog/introducing-timeseries/An MIT-licensed, Prometheus-compatible timeseries database built on SlateDB, bringing the operating model and cost structure of object-store-native systems to the Prometheus and Grafana ecosystem.Thu, 16 Apr 2026 00:00:00 GMTtimeseriesprometheusslatedbannouncementApurva Mehtahttps://www.opendata.dev/blog/manifesto/https://www.opendata.dev/blog/manifesto/The OpenData ManifestoThu, 01 Jan 2026 00:00:00 GMTmanifestoThe OpenData Contributors