StackMap
Subscribe

Chroma vs zvec

Open-source embedding database for building AI apps with retrieval. — versus — Alibaba's open-source in-process vector database: billion-scale similarity search embedded in your app, with DiskANN on-disk indexing, native full-text search and hybrid retrieval.

The curated verdict

Same job — the embedding store under a RAG pipeline. Chroma is the Python-native developer default; Zvec is the in-process C++ engine betting on raw speed, DiskANN memory economics and built-in hybrid retrieval.

Chromazvec
Stars29k15k
Forks2.4k931
LanguagePythonC++
LicenseApache-2.0Apache-2.0
Last activity2 days agoyesterday
Topicsrag, memoryrag
Curated connections81

Chroma — the curator's take

Open-source embedding database for building AI apps with retrieval.

zvec — the curator's take

The 'SQLite of vector search' position, executed with Alibaba-scale engineering: runs inside your process (no server to operate), DiskANN keeps memory flat at large scale, and v0.5 added native FTS + hybrid retrieval so one MultiQuery spans dense, sparse, filters and text — no external search engine. Battle-tested internally before open-sourcing. NOT for multi-service architectures needing a shared, network-accessible store with auth and replication — in-process is the whole point and the whole limitation; C++ core with Python/Go/Rust SDKs, so debugging beneath the binding is not for everyone.