zvec

Good for

• Embed a lightweight, fully local vector database into an application, with no server
• Run similarity search over dense and sparse vectors with a range of index types
• Do full-text search and fuse it with vector similarity and structured filters in one query
• Use it as a backend for LLM memory or semantic search over local docs and code

Getting started

1. Run npx skills add alibaba/zvec
2. Install the SDK for your language, e.g. pip install zvec for Python or npm install @zvec/zvec for Node.js
3. Define a collection with CollectionSchema, then create_and_open it
4. Insert documents, then query by vector similarity to get results

Before you install

An open-source vector database battle-tested inside Alibaba, supporting Linux, macOS, Windows, Android and iOS. The Python SDK needs 64-bit Python 3.10 to 3.14.

Summarized by AI from the project docs; check the official docs before relying on it.