Vectra

A local, file-backed vector database with cross-language gRPC access.

Get Started View on GitHub


Vectra works like a local Pinecone or Qdrant: each index is a folder on disk, loaded into memory for fast queries. Filter by metadata using MongoDB-style operators, rank by cosine similarity, and get results in under a millisecond for small indexes.

Key capabilities

   
Zero infrastructure Everything lives in a local folder — no servers or managed services
Fast lookups Sub-millisecond to low-millisecond latency
Pinecone-style filtering MongoDB query operators for metadata filtering
Multiple embeddings OpenAI, Azure, OSS endpoints, or local HuggingFace models (no API key)
Pluggable storage Filesystem, IndexedDB (browsers), in-memory, or custom backends
Browser & Electron Dedicated vectra/browser entry point with local embeddings and IndexedDB
CLI included Manage indexes, serve gRPC, watch folders from the terminal
Cross-language Built-in gRPC server with bindings for Python, C#, Rust, Go, Java, TypeScript
Flexible format JSON (human-readable) or Protocol Buffers (40-50% smaller)

Choose your path

I want to… Start here
Store items with vectors I generate myself Getting Started — LocalIndex
Ingest raw text and let Vectra chunk + embed Getting Started — LocalDocumentIndex
Run in a browser or Electron Storage — Running in the Browser
Access Vectra from Python, C#, Rust, etc. gRPC Server
Use the CLI without writing code CLI Reference

What’s New in v0.14.x

  • Browser & Electron supportvectra/browser entry point with IndexedDBStorage and TransformersEmbeddings
  • Local embeddingsLocalEmbeddings and TransformersEmbeddings run HuggingFace models with no API key
  • Protocol Buffers — opt-in binary format, 40-50% smaller files
  • gRPC servervectra serve exposes 19 RPCs for cross-language access
  • FolderWatcher — auto-sync directories into a document index
  • Language bindingsvectra generate scaffolds clients for 6 languages

See the Changelog for breaking changes and migration details.

Documentation

Guide Description
Getting Started Install, requirements, quick start with both index types
Core Concepts Index types, metadata filtering, on-disk layout, storage backends
Embeddings Guide Choose and configure an embeddings provider
Document Indexing Chunking, retrieval, hybrid search, FolderWatcher
CLI Reference All CLI commands, flags, and embeddings provider config
API Reference TypeScript API overview with links to typedoc
Best Practices Performance tuning, operational tips, troubleshooting
Storage Pluggable backends, custom storage, browser/IndexedDB, formats
gRPC Server Cross-language access, service API, language bindings
Changelog Breaking changes, migration guides, version compatibility
Tutorials End-to-end walkthroughs: RAG pipeline, browser app, gRPC, custom storage, folder sync