#9 · Primary category: Vector Databases

zvec

agent-skills db embedded faiss hnsw llm-memory local rag search-engine semantic-search similarity-search vector-database vector-db

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

Project last updated:08/28/26

GitHub Stars

15.5K

Forks

984

Contributors

32

License

Apache-2.0

Why we included this project

Zvec is a vector database that runs inside your application as a library instead of as a separate server. You install one package and you can start indexing and querying vectors right away, with no daemon to run and no external infrastructure to provision. That makes it a good fit for local development, embedded apps, and edge deployments where a heavyweight service is overkill. It handles both dense and sparse embeddings, supports hybrid search that combines semantic similarity with structured filters, and uses write-ahead logging so your data survives crashes. It has been exercised inside Alibaba's production workloads, so it scales to large collections with low search latency, and it can also be embedded into an existing SQL database as a dedicated vector search engine.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category