Data & context
vectrize
A local Markdown retrieval daemon with hybrid search and a CLI that agents can invoke directly.
Overview
Research summary
vectrize is a command-line search tool for local Markdown collections. It splits documents into chunks while retaining heading context, computes multilingual BGE-M3 embeddings, and combines vector retrieval with BM25 keyword search. A background daemon watches registered folders and updates changed content. Its index uses SQLite with sqlite-vec and FTS5, and agents can consume JSON search results or use the supplied skill. The embedding model downloads on first use, after which retrieval runs locally. The README documents native macOS and Linux support and WSL2 guidance for Windows users.
Repository summary
- Stars
- Unavailable
- Open issues
- Unavailable
- Last push
- Unavailable
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Version
- Unavailable
Recorded catalogue figures. View repository data and provenance →
Classification
Pricing & services
Paid services unknown
Whether the provider offers paid products or services has not been established.
Licence scope
Cargo.toml explicitly offers these alternative licenses. The separately downloaded embedding model retains its own terms.
Implementation
Recorded implementation details and interfaces for vectrize.
Implementation details
Rust CLI and watcher using local embeddings, SQLite, sqlite-vec, and FTS5
- Languages
- Rust
- Repository type
- source
Recorded interfaces and capabilities
Licence scope
Cargo.toml explicitly offers these alternative licenses. The separately downloaded embedding model retains its own terms.
Repository
Repository snapshots, release information and recorded maintenance signals.
Repository snapshot
- Stars
- Unavailable
- Open issues
- Unavailable
- Last push
- Unavailable
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Archived
- Not recorded
Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).
Maintenance and provenance
- Catalogue snapshot
- 2026-10-06
Documentation
Recorded references and research provenance for this entry.
Recorded sources 6
- https://github.com/pablofrr/vectrize Project page · Linked repository · Research reference
- https://crates.io/crates/vectrize Research reference
- https://github.com/pablofrr/vectrize/blob/master/README.md Research reference
- https://github.com/pablofrr/vectrize/blob/master/LICENSE-APACHE Research reference
- https://github.com/pablofrr/vectrize/blob/master/LICENSE-MIT Research reference
- https://github.com/pablofrr/vectrize/blob/master/Cargo.toml Research reference
Research metadata
- Research date
- 2026-10-02
- Catalogue snapshot
- 2026-10-06