Home > Databases > vectordbz

vectordbz

A modern desktop application for exploring, managing, and analyzing vector databases

ai aitools chroma database-management embeddings milvus pgvector pinecone typescript

Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

A modern desktop application for exploring, managing, and analyzing vector databases

README

VectorDBZ

Open-source desktop client for vector databases

VectorDBZ lets you connect to local or cloud vector database instances, explore collections, run vector and hybrid searches, and visualize embeddings in 2D/3D — all from a native desktop app, no infrastructure required.

Supported Databases

Database	Minimum Version
Qdrant	`v1.7+`
Weaviate	`v1.19+`
Milvus	`v2.3+`
ChromaDB	`v0.4+`
Pinecone	Latest
pgvector (PostgreSQL)	`PostgreSQL 11+` with `pgvector` extension
Elasticsearch	`v8.x`
RedisSearch (Redis Stack)	`v2.0+`

Installation

Homebrew (macOS)

brew tap vectordbz/vectordbz
brew install --cask vectordbz

Direct Download

Download the latest release →

Platform	Package
Windows	`.exe` installer (Windows 10+)
macOS Intel	`darwin-x64` zip (macOS 10.15+)
macOS Apple Silicon	`darwin-arm64` zip (macOS 10.15+)
Linux	`.deb` or `.rpm` (Ubuntu 18.04+, Fedora 32+)

macOS Note

The app is not code-signed. On first launch, right-click → Open → click Open in the dialog.

If you see "VectorDBZ is damaged", run:

xattr -cr /Applications/VectorDBZ.app

Development

See docs/DEVELOPMENT.md for the full setup guide — prerequisites, running the app locally, seeding test data, and available scripts.

Quick start:

git clone https://github.com/vectordbz/vectordbz.git
cd vectordbz/app
npm ci
npm run start

Contributing

Contributions are welcome — new database integrations, bug fixes, and feature improvements.

Read CONTRIBUTING.md to get started
Use the step-by-step guide to add a new database integration
Browse open issues
Open an issue before starting large changes

Support

Issues & Questions — GitHub Issues
Release Notes — GitHub Releases

Release History

Version	Changes	Urgency	Date
v0.0.21	## VectorDBZ v0.0.21 ### Fixed - macOS Intel (x64) download is back. Earlier releases were missing the Intel build, so users on Intel Macs had no compatible download. The release pipeline now builds and publishes the macOS Intel installer alongside Apple Silicon (arm64), Windows, and Linux. ### Downloads - macOS (Apple Silicon / arm64) — `.zip` - macOS (Intel / x64) — `.zip` - Windows (x64) — Setup `.exe` - Linux (x64) — `.deb` / `.rpm` Auto-updates are deli	High	5/29/2026
v0.0.20	Bug Fixes ChromaDB: Fixed connection failure when using default tenant and database — When connecting to a local ChromaDB instance, the tenant and database fields from the connection config are now properly passed to the client. Previously, omitting these values caused a connection error even when ChromaDB was running correctly with its defaults. ([#11](https://github.com/vectordbz/vectordbz/issues/11))	High	4/28/2026
v0.0.19	## Bug Fixes - Weaviate: fixed GraphQL error for collections with object-typed properties — Querying collections that contain an `object` property (e.g. a `payload` field with nested sub-fields) would fail with `Field "X" of type "..." must have a sub selection`. The document list and search views now correctly expand object fields into their nested sub-selections based on the collection schema, while scalar fields continue to work as before.	Medium	4/1/2026
v0.0.18	New Database: RedisSearch VectorDBZ now supports Redis Stack / RedisSearch as a vector database backend. Vector search — Dense vector similarity search with FLAT and HNSW index types Payload filtering — Filter search results by metadata fields Collection browsing — Browse and inspect RedisSearch indexes and their documents Connection — Connect via host/port with optional password authentication This brings the total number of supported databases to 8: Qdrant, Weaviate, Milvus, ChromaDB,	Medium	3/27/2026
v0.0.17	# VectorDBZ v0.0.17 Elasticsearch support, richer search, and a new 3D visualization experience. --- ## Highlights ### 🔍 Elasticsearch & full-text search Connect to Elasticsearch 8.x for vector search, lexical (full-text) search, and hybrid search with RRF. Dense and sparse vectors, sort by payload (including text via `.keyword`), and client-side RRF fallback when the server license doesn’t include RRF. Use keywords alongside vectors—supported on Weaviate (BM2	Low	1/30/2026
v0.0.16	# VectorDBZ v0.0.16 ## What's New ### Sparse Vector Support VectorDBZ now supports sparse vectors for keyword-based search, enabling more precise document retrieval. Sparse vectors efficiently represent keyword matches (BM25/TF-IDF style) where most elements are zero, making them ideal for exact term matching and keyword-based search scenarios. Supported Databases: - Qdrant - Full sparse vector support with indices and values format - Milvus - SparseFloatVector data	Low	1/23/2026
v0.0.15	# VectorDBZ v0.0.15 ## What's New ### Search History & Comparison Stay on top of your vector search workflow with comprehensive search history tracking. VectorDBZ now remembers your recent searches, allowing you to quickly restore previous queries and compare results across different search configurations. The new comparison view provides clear insights into how parameter changes affect your search results, complete with overlap analysis and performance metrics. ### Advanced Visualizat	Low	1/12/2026
v0.0.14	# VectorDBZ v0.0.14 ## 🎉 New: Pinecone Support (Partial) Pinecone integration is now available! Connect to your Pinecone indexes and manage your vector data. Available features: - Connect using API key - View and create indexes (serverless & pod-based) - Browse namespaces - Search, insert, update, and delete documents - Metadata filtering Note: Dense vectors only for now. Sparse vector support coming soon. --- ## ⚠️ Analysis Tab Temporarily Disabled The Analysi	Low	1/10/2026
v0.0.13	# VectorDBZ v0.0.13 Release Notes ## 🎉 New Features ### ✨ pgvector (PostgreSQL) Support We're excited to announce full support for pgvector - PostgreSQL's vector extension! You can now connect to PostgreSQL databases with the pgvector extension and manage your vector data alongside your relational data. Key Features: - ✅ Full CRUD operations (Create, Read, Update, Delete) - ✅ Vector similarity search with multiple distance metrics (Cosine, L2, Inner Product) - ✅ Support for	Low	1/4/2026
v0.0.12	# 🚀 VectorDBZ v0.0.12 ## ✨ What's New ### Embedding Generation in Search Tab Generate embeddings directly in the Search tab! Create custom embedding functions to integrate with any API (OpenAI, Hugging Face, Cohere, Anthropic, Google, Ollama, local models, and more). Generate embeddings from text or file uploads, and they're automatically copied to the search field for immediate similarity searches. Key Features: - 🎯 Custom embedding functions with JavaScript support - 📝 Text	Low	1/1/2026

Dependencies & License Audit

Loading dependencies...

Similar Packages

CodeRAGBuild semantic vector databases from code and docs to enable AI agents to understand and navigate your entire codebase effectively.main@2026-06-02

WeKnoraLLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.v0.6.1

mem9Enable AI agents to retain memory across sessions using persistent storage designed for continuous context retention.main@2026-06-05

txtai💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflowsv9.10.0

modelenceModelence is a full-stack framework for building production web apps with a built-in database, authentication and monitoring. Modelence is opinionated and AI agent-first, which means it's optimized fomodelence@0.19.0

More in Databases

orbitOne API for 20+ LLM providers, your databases, and your files — self-hosted, open-source AI gateway with RAG, voice, and guardrails.

alibabacloud-adb20211201Alibaba Cloud adb (20211201) SDK Library for Python

milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search

WeKnoraLLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.