BigHugger
GH Repository · alibaba

zvec

A lightweight, lightning-fast, in-process vector database

stars
15,958
30-day movement
+5217/day
Related entries
60
Connections
1
pythonC++fulltext-searchftsragagent-skillsembeddedfaissvector-databasehnswsemantic-searchlocalllm-memorysearch-enginedbsimilarity-searchvector-db

zvec is a lightweight, in-process vector database written in C++ with a Python toolchain. It ships as a library for similarity search, semantic search, and full-text search within a single local process.

Use it when you want vector search embedded directly in your application without running a separate database service.

Use it to

  • Store and query embeddings locally for RAG
  • Add semantic search to a Python application
  • Build LLM memory backed by vector and full-text search
  • Prototype similarity search without server infrastructure

For Python developers building local RAG or agent applications

Role
rag
Language
C++
Licence
Apache-2.0
Forks
998
Open issues
30
Last push
2026-09-17
Latest release
v0.1.0 · 2025-12-31
topicsvector-databaseragsimilarity-searchembeddedsemantic-searchfulltext-search