← Discover
Discover · GitHub · Zvec↑ +156 today

Fast in-app vector database

Developed by Alibaba, zvec is a lightweight and high-speed in-process vector database solution written in C++. It aims to increase system performance by allowing applications to process vector data directly in memory.

Updates

  • August 24, 2026: Stars 15,356 → 15,504, latest release v0.7.0 (August 24, 2026).
  • August 2, 2026: Stars 10,691 → 15,356, latest release v0.6.0 (July 20, 2026).

What you get

  • Local operating architecture that does not require a server
  • Millisecond search speed over billions of vectors
  • Vector, text and hybrid search support

Installation

Installation for Python
pip install zvec
Installation for Node.js
npm install @zvec/zvec

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

I need to create a collection using the Zvec library. Can you create sample code in Python that allows me to define a schema, add appropriate vector data to that schema, and then search with a specific vector query? Please use a structure that specifies the file path for the data to be persistent.

Related dictionary terms

In-process Vector DatabaseVector DatabaseIn-processDatabaseArtificial Intelligence
Who it is forIt is suitable for developers who want to add a high-performance, native vector search capability to their applications without installing an external server.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-17: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.