RyanCodrai/turbovec

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A vector index written in Rust with Python bindings, built on Google Research's TurboQuant quantizer. It adds vectors without a training step, saves changes incrementally, filters by id at search time and runs fully locally.

How it helps ATF

Could be a reference for local vector search behind Company Brain, where results must stay within access scope. Its id allowlist filter at search time is worth comparing for permission-aware retrieval.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• GoogleCloudPlatform/knowledge-catalog
  Tools, agents and samples for Google Cloud Knowledge Catalog, formerly Dataplex, a data catalog and metadata platform that provides a knowledge graph over structured and unstructured data. The samples show context management, enrichment and retrieval for AI agents.
• lfnovo/open-notebook
  Open Notebook is an open-source, self-hosted alternative to Google Notebook LM. It gathers PDFs, videos, audio and web pages, searches them by full text and vectors, lets users chat with that content and generates multi-speaker podcasts.
• StarTrail-org/PixelRAG
  PixelRAG renders web pages, PDFs and images as screenshots and runs retrieval over the images directly, so tables, charts and layout that HTML parsing drops stay intact. It is the official code for a research paper.
• MinishLab/semble
  Semble is a code search library for agents that returns only the relevant code snippets for a natural-language query. It runs on CPU without API keys or external services, and works as an MCP server, CLI or sub-agent.
• semantica-agi/semantica
  A Python library that ingests enterprise data, extracts key information, builds a context graph and knowledge graph, and runs graph analytics and reasoning over them. It keeps decision provenance for end-to-end traceability.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.