| Vector Database | Open Source? | License | GitHub stars or other traffic numbers | Developed in (language) | Summary | Business Model | Embeds / Uses | founding / first released date | In-memory Unterstützung | Sharding | Index Types | Consistency Model | Benchmarks (Performance?) | Approximate Nearest Neighbor (ANN) | Funding | Who's behind it | HQ in |
| Marqo AI | Y | Apache-2.0 | 2.8k stars | Python | A tensor-based cloud-native commercial Open Source search and analytics engine. | Open SaaS | Tensor-based | ❔ | Y | HNSW | - | undisclosed preseed in May 2022 | S2Search Australia Pty Ltd | Australia | |||
| Weaviate | Y | BSD | 5.6k stars | Assembly, C++, GoLang | Weaviate is a commercial Open Source cloud-native vector database that stores both objects and vectors. | Open SaaS | ❔ | started in 2018 as a traditional graph database, first released in 2019 | N | Y | a custom HNSW algorithm that supports CRUD | Eventual Consistency | not comparative, just evaluating their own performance | Y (It can support multiple ANN algorithms as long as they support full CRUD) | 67.7M USD, series B | SeMI Technologies | EU |
| Chroma | Y | Apache-2.0 | 4.4k stars | Python & Typescript | Chroma is a Commercial Open Source vector database | Preparing a (Partly Open) SaaS model* [Commercial Open Source] | HNSW lib, DuckDB; based on ClickHouse | looks like 2022 | N | HNSW | - | Y | 20.3M USD, seed | Chroma Inc. | US | ||
| Qdrant | Y | Apache-2.0 | 6.6k stars | Rust | Qdrant is a Commercial Open Source vector similarity search engine and vector database | Open SaaS | RocksDB | first released: 2021 | Y | Y | HNSW | Eventual Consistency, tunable consistency | compares to weaviate, milvus, elastic (note: redis took too long to complete) | Y | 9.8M € | Qdrant Solutions GmbH | EU (D) |
| Milvus | Y | Apache-2.0 | 18k stars | GoLang & Python | Milvus is a cloud-native Commercial Open Source vector database | (Partly Open) SaaS* [Commercial Open Source] | Initially a blog post from them said SQLite, but meanwhile they
said RocksDB; was maybe exchanged? they also have a ChatGPT-Cache that is build on SQLite and say "Milvus uses SQLite or MySQL to manage metadata" |
founded 2017, first released: 2019 | N | Y | ANNOY; HNSW; IVF_PQ; IVF_SQ(; IVF_FLAT; FLAT; IVF_SQ8_H; RNSG | Milvus supports four consistency levels: strong, bounded staleness, session, and eventually. The default consistency level in Milvus is bounded staleness. | not comparative | Y | 113M USD, series B | Zilliz | US |
| Vespa | Y | Apache-2.0 | 4.4k stars | Java & C++ | Vespa is a Commercial Open Source vector database by Yahoo! It is a search engine which supports vector search, lexical search, and search in structured data | Open SaaS | ❔ | originally a web search engine (alltheweb), acquired by Yahoo! in 2003 and later developed into and open sourced as Vespa in 2017 | maintains disk and memory structures for documents | Y | HNSW; BM25 | Eventual Consistency | not comparative | Y | Yahoo! | Yahoo! | US |
| Vald | Y | Apache-2.0 | 1.2k | GoLang | Vald is a cloud-native Open Source distributed approximate nearest neighbor (ANN) dense vector search engine | Community project, currently looks like no commercial interests are pursued | uses the vector search engine NGT | Technology incubation at Yahoo! Japan Corporation, development was stared in 2019 | ❔ | Y | Distributed Index, asynchronous indexing | N/A | not comparitive | Y (NGT) | Yahoo Japan Corporation | Yusuke Kato and Kiichiro Yukawa (Yahoo Japan Corporation) | Japan |
| Pinecone |
N | Proprietary | NA | Pinecone is a fully managed vector database that specializes in enabling semantic search capabilities | SaaS | built on top of Faiss | first released in 2019 | N | Y | proprietary | Eventual Consistency | more programming language comparison for vector databases | Y (proprietary), plus KNN (with Faiss) | 138M, series B | Pinecone Systems Inc | US |