Hosted vector database for similarity search. Um produto fechado de Pinecone Systems.
| Ferramenta | Substituição | Estrelas | Licença | Termos | Auto-hospedado | Linguagem | Última release | Último push |
|---|---|---|---|---|---|---|---|---|
| Milvus | Substituição completa | 46k | Apache-2.0 | Código aberto | Sim | Go | v3.0.2 | 2026-10-06 |
| Qdrant | Substituição completa | 35k | Apache-2.0 | Código aberto | Sim | Rust | v1.19.2 | 2026-10-06 |
| Weaviate | Substituição completa | 17k | Other | Open core | Sim | Go | v1.39.9 | 2026-10-06 |
| Chroma | Parcial | 29k | Apache-2.0 | Código aberto | Sim | Rust | 1.5.9 | 2026-10-05 |
| pgvector | Parcial | 23k | Other | Código aberto | Sim | C | v0.8.7 | 2026-10-06 |
| LanceDB | Parcial | 12k | Apache-2.0 | Código aberto | Sim | Rust | v0.39.0 | 2026-10-06 |
| Infinity | Parcial | 4.7k | Apache-2.0 | Código aberto | Sim | C++ | v0.7.3 | 2026-09-23 |
| pgvectorscale | Parcial | 3.1k | PostgreSQL | Não verificado | Sim | Rust | 0.9.1 | 2026-10-01 |
| Vald | Parcial | 1.7k | Apache-2.0 | Código aberto | Sim | Go | v1.8.0 | 2026-10-06 |
9 alternativas
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Distributed vector database for billions of vectors, or embedded as Milvus Lite.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Vector search with payload filtering, quantisation and hybrid search.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Vector and hybrid search with built-in vectoriser modules.
Search infrastructure for AI
Embedded or client-server vector store, aimed at LLM applications.
Open-source vector similarity search for Postgres
Vector similarity search inside PostgreSQL, next to your relational data.
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
Embedded vector and full-text search over Lance files on local disk or object storage, without a server to run.
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
Dense, sparse, tensor and full-text search in one engine, with filtering.
Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.
Adds a disk-based StreamingDiskANN index and label filtering to pgvector inside PostgreSQL.
Vald. A Highly Scalable Distributed Vector Search Engine
Distributed approximate nearest-neighbour search that runs on Kubernetes.