Data

Databases, query engines, pipelines, formats and analytics.

6 projects

Data

turbovec fits 10M vectors in 4 GB and outruns FAISS

RyanCodrai/turbovec

A Rust index built on Google Research's TurboQuant: no training step, hand-written NEON and AVX-512 kernels, crash-safe incremental saves and filtered search.

★ 16.9K · Rust · September 13, 2026
Data

Hivemind mines your team's traces into shared skills

activeloopai/hivemind

Sessions become searchable traces, repeated patterns become SKILL.md files, and every agent on the team inherits them. Benchmarked 25% cheaper on LoCoMo.

★ 1.6K · TypeScript · August 30, 2026
Data

Zvec is a vector database that lives inside your process

alibaba/zvec

Alibaba's embedded C++ engine does dense, sparse, full-text and hybrid search with WAL durability, bringing SQLite's deployment model to retrieval.

★ 15.4K · C++ · August 28, 2026
Data

Hindsight is agent memory that tries to learn, not recall

vectorize-io/hindsight

A memory system claiming state of the art on LongMemEval, with the rare detail that outside researchers reproduced the score instead of the vendor asserting it.

★ 20K · Python · August 23, 2026
Data

PixelRAG retrieves over screenshots instead of parsed text

StarTrail-org/PixelRAG

A Berkeley project that renders pages as images and searches them visually, keeping the tables, charts and layout that HTML parsing throws away.

★ 9.5K · Python · August 18, 2026
Data

GeoLibre runs 1,000+ GIS tools in the browser, offline

opengeos/GeoLibre

A cloud-native GIS built on Tauri, MapLibre and DuckDB-WASM that ships the WhiteboxTools toolbox to WebAssembly, for desktop, mobile, browser and Jupyter.

★ 6.1K · TypeScript · August 4, 2026