RepoRadar
Leave a Tip
Item detail

alibaba/zvec

zvec is an Apache-2.0 lightweight, in-process vector database from Alibaba Group that ships production-grade low-latency similarity search with no server to run. The v0.5.0 release (June 12, 2026) adds native full-text search, hybrid vector+text queries via a single MultiQuery, a DiskANN on-disk index for large datasets, plus first-party Go and Rust SDKs alongside the Python and Node packages. Bat

Open source →Back to radar
Score8.4
Popularity95.0
Risknone
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum9.0
Maturity8.5
Open-source/build8.4
Evidence7.2
Workflow potential9.5
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developers building local-first RAG or agent-memory apps who do not want to stand up a vector server: pip install zvec, open a collection in-process, and run dense-vector, sparse-vector, full-text, or hybrid MultiQuery against it from Python, Node, Go, or Rust without an external process. The DiskANN index means the same library now scales to collections that exceed RAM.

Who should use it

developers building local-first RAG or agent-memory apps who do not want to run a separate vector serverteams that want dense + sparse + full-text + scalar-filter queries in one library instead of stitching FAISS + a search engineGo and Rust users who finally have a first-party vector-DB SDK without an HTTP client wrapperprojects whose collections exceed RAM and need an on-disk index (DiskANN in v0.5) without switching to a server stackAlibaba / China-cloud users who want a vector DB built and battle-tested in the same ecosystem

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

No inherent user-impacting risk is flagged from the captured evidence.

Evidence links

Closest alternatives / related signals

vector-databaseembeddedin-processalibabasimilarity-searchfull-text-searchhybrid-searchdiskann