# vectra > A lightweight, file-backed vector database for Node.js and browsers with Pinecone-compatible filtering and hybrid BM25 search. Latest version **0.15.0** (published 2026-05-24) · MIT license · 0 weekly downloads ## Install ```sh npm install vectra pnpm add vectra yarn add vectra bun add vectra ``` Provides the command `vectra`. ## Health **Score 65/100 (B)** — status: active. Positive: has types; esm support; no vulnerabilities; high maintenance score; high quality score. Warnings: low downloads; pre 1.0. ## Facts | | | |---|---| | Version | 0.15.0 | | Published | 2026-05-24 | | First published | 2023-05-01 | | Weekly downloads | 0 | | License | MIT | | TypeScript types | bundled | | Module format | ESM + CommonJS | | Node | >=22.x | | Dependencies | 13 | | Unpacked size | 2.1 MB | | Known vulnerabilities | 0 | | Install scripts | no | | GitHub stars | 632 | | Author | Steven Ickman | | Maintainers | stevenic | | Keywords | vector-database, embeddings, semantic-search, rag, retrieval-augmented-generation, openai, azure-openai, transformers, local-embeddings, cosine-similarity, bm25, hybrid-search, local-database, llm, ai, browser, electron | ## Links - npm: https://www.npmjs.com/package/vectra - Repository: https://github.com/Stevenic/vectra - Homepage: https://github.com/Stevenic/vectra#readme - Issues: https://github.com/Stevenic/vectra/issues - npm.io page: https://npm.io/package/vectra ## Dependencies (13) - [uuid](https://npm.io/package/uuid.md) ^13.0.0 - [yargs](https://npm.io/package/yargs.md) ^18.0.0 - [buffer](https://npm.io/package/buffer.md) ^6.0.3 - [dotenv](https://npm.io/package/dotenv.md) ^17.4.1 - [openai](https://npm.io/package/openai.md) ^6.33.0 - [cheerio](https://npm.io/package/cheerio.md) ^1.0.0 - [turndown](https://npm.io/package/turndown.md) ^7.2.0 - [wink-nlp](https://npm.io/package/wink-nlp.md) ^2.3.2 - [@grpc/grpc-js](https://npm.io/package/@grpc/grpc-js.md) ^1.14.3 - [gpt-tokenizer](https://npm.io/package/gpt-tokenizer.md) ^3.4.0 - [json-colorizer](https://npm.io/package/json-colorizer.md) ^3.0.1 - [@grpc/proto-loader](https://npm.io/package/@grpc/proto-loader.md) ^0.8.0 - [wink-bm25-text-search](https://npm.io/package/wink-bm25-text-search.md) ^3.1.2 ## Alternatives - [@expo/fingerprint](https://npm.io/package/@expo/fingerprint.md) — 6.2M weekly downloads - [@azure/monitor-opentelemetry-exporter](https://npm.io/package/@azure/monitor-opentelemetry-exporter.md) — 850.0K weekly downloads - [@azure/monitor-opentelemetry](https://npm.io/package/@azure/monitor-opentelemetry.md) — 624.0K weekly downloads - [@posthog/ai](https://npm.io/package/@posthog/ai.md) — 423.3K weekly downloads - [fakefilter](https://npm.io/package/fakefilter.md) — 63.9K weekly downloads ## Recent versions - 0.15.0 (latest) — 2026-05-24 - 0.14.0 — 2026-04-03 - 0.12.3 — 2026-01-13 - 0.12.2 — 2026-01-09 - 0.12.1 — 2026-01-09 - 0.12.0 — 2026-01-09 - 0.11.1 — 2025-05-12 - 0.11.0 — 2025-05-07 - 0.10.1 — 2025-05-07 - 0.10.0 — 2025-03-28 - 0.9.0 — 2024-08-17 - 0.7.6 — 2024-04-05 - 0.7.5 — 2024-04-05 - 0.7.4 — 2024-04-05 - 0.7.3 — 2024-04-05 - … 22 more at https://npm.io/package/vectra/versions ## README # Vectra: a local vector database [![npm version](https://img.shields.io/npm/v/vectra.svg)](https://www.npmjs.com/package/vectra) [![Build](https://github.com/Stevenic/vectra/actions/workflows/ci.yml/badge.svg)](https://github.com/Stevenic/vectra/actions/workflows/ci.yml) [![Coverage Status](https://coveralls.io/repos/github/Stevenic/vectra/badge.svg?branch=main)](https://coveralls.io/github/Stevenic/vectra?branch=main) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Agent Ready](https://img.shields.io/badge/Agent-Ready-blue.svg)](#agent-ready) Vectra is a local, file-backed, in-memory vector database with an optional gRPC server for cross-language access. Each index is a folder on disk — queries use MongoDB-style metadata filtering and cosine similarity ranking, with sub-millisecond latency for small indexes. ## What's New in Vectra 0.14+ - **Browser & Electron support** — `vectra/browser` entry point with `IndexedDBStorage` and `TransformersEmbeddings` - **Local embeddings** — `LocalEmbeddings` and `TransformersEmbeddings` run HuggingFace models with no API key - **Protocol Buffers** — opt-in binary format, 40-50% smaller files - **gRPC server** — `vectra serve` exposes 19 RPCs for cross-language access - **FolderWatcher** — auto-sync directories into a document index - **Language bindings** — `vectra generate` scaffolds clients for 6 languages - **0.15: Performance improvements** — skip-if-unchanged document upserts, shallow-clone transactional snapshots, heap-based top-K query ranking, parallel metadata loads, and O(N) batch chunk deletion See the [Changelog](https://stevenic.github.io/vectra/changelog) for breaking changes and migration details. ## Install ```sh npm install vectra ``` ## Quick Example ```ts import { LocalDocumentIndex, OpenAIEmbeddings } from 'vectra'; const docs = new LocalDocumentIndex({ folderPath: './my-index', embeddings: new OpenAIEmbeddings({ apiKey: process.env.OPENAI_API_KEY!, model: 'text-embedding-3-small', maxTokens: 8000, }), }); if (!(await docs.isIndexCreated())) { await docs.createIndex({ version: 1 }); } await docs.upsertDocument('doc://readme', 'Vectra is a local vector database...', 'md'); const results = await docs.queryDocuments('What is Vectra?', { maxDocuments: 5 }); if (results.length > 0) { const sections = await results[0].renderSections(2000, 1, true); console.log(sections[0].text); } ``` ## Documentation Full docs at **[stevenic.github.io/vectra](https://stevenic.github.io/vectra/)**: | Guide | Description | |-------|-------------| | [Getting Started](https://stevenic.github.io/vectra/getting-started) | Install, requirements, quick start with both index types | | [Core Concepts](https://stevenic.github.io/vectra/core-concepts) | Index types, metadata filtering, on-disk layout | | [Embeddings Guide](https://stevenic.github.io/vectra/embeddings) | Choose and configure an embeddings provider | | [Document Indexing](https://stevenic.github.io/vectra/documents) | Chunking, retrieval, hybrid search, FolderWatcher | | [CLI Reference](https://stevenic.github.io/vectra/cli) | All CLI commands, flags, and provider config | | [API Reference](https://stevenic.github.io/vectra/api-reference) | TypeScript API overview | | [Best Practices](https://stevenic.github.io/vectra/best-practices) | Performance tuning, troubleshooting | | [Storage](https://stevenic.github.io/vectra/storage) | Pluggable backends, browser/IndexedDB, serialization formats | | [gRPC Server](https://stevenic.github.io/vectra/grpc) | Cross-language access and language bindings | | [Changelog](https://stevenic.github.io/vectra/changelog) | Breaking changes and migration guides | | [Tutorials](https://stevenic.github.io/vectra/tutorials/) | RAG pipeline, browser app, gRPC, custom storage, folder sync | | [Samples](./samples/) | Runnable examples: quickstart, RAG, browser, SQLite storage, gRPC, folder watcher | ## Agent Ready Vectra ships an [`llms.txt`](https://github.com/Stevenic/vectra/blob/main/llms.txt) file that gives coding agents everything they need to integrate Vectra into your project. Point your agent at it and let it do the work: ``` Read the llms.txt file at https://raw.githubusercontent.com/Stevenic/vectra/main/llms.txt and then add Vectra support to this project. Use LocalDocumentIndex for document storage and retrieval. ``` The `llms.txt` file covers all exports, index types, CLI commands, gRPC bindings, and on-disk format — enough for any coding agent to scaffold a working integration without browsing docs. ## License MIT License. See [LICENSE](LICENSE). ## Contributing See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines. Please review our [Code of Conduct](CODE_OF_CONDUCT.md). --- _Source: https://npm.io/package/vectra · Machine-readable twin of the npm.io package page. Health data is recomputed on every publish._