Back to directory

Urna

A single-file, offline-first vector database for Rust that stores embeddings, source text and search indices in one verifiable, reproducible file with stable content-hash citations.

Urna

Urna packages a vector database into one file: a container holding text chunks, embeddings, source spans, indices and the search contract. A Rust runtime memory-maps the file, checks its hashes, and answers queries with exact cosine scores plus a content-hash citation for every hit.

Files are self-contained like a SQLite database, verifiable through per-section and per-file SHA-256 hashes, and reproducible: the same chunks and model produce a byte-identical file on any machine. The runtime works fully offline.

A companion Python tool builds the files, while the Rust runtime serves them; a terminal UI opens a corpus, validates it, and lets a user ask it questions interactively. It installs via Homebrew, npm, Cargo, a shell script or pip.

More in Databases

See all 294
  • SQLBraid

    clickin.github.io

    A SQL-first data-access toolkit for TypeScript that keeps ordinary SQL visible in tagged template literals, binds interpolated values safely by default, supports readable conditional SQL directives, and lets a schema validate the returned rows.

  • A SQL-style query language and toolchain for the Qdrant vector database, covering dense, sparse and hybrid search, filtering and multitenancy, with the same grammar running from a CLI, Python, Node.js, Rust, WebAssembly and an in-process edge engine.

  • Fast Knowledge

    github.com

    A self-hosted, Java-based knowledge base for small and mid-sized organizations, turning internal documents into a searchable, question-answerable and audit-exportable knowledge asset with hybrid retrieval and Docker deployment.