Qdrant

Qdrant is an open-source vector search engine written in Rust, known for high performance, advanced filtering, and memory-efficient quantization. It can be self-hosted for free under Apache 2.0 or run as Qdrant Cloud, which bills hourly on provisioned resources rather than per query. It is a cost-efficient, performant choice for RAG and similarity search.

Qdrant is an open-source vector similarity search engine and database written in Rust, designed for speed, memory efficiency, and rich filtering. It stores vectors with structured payloads and supports fast approximate nearest-neighbor search combined with detailed metadata filters, making it well suited to production RAG, semantic search, recommendations, and anomaly detection. Qdrant's Rust foundation gives it strong performance and predictable resource usage, and it supports features like quantization (to shrink memory footprint), sparse and hybrid search, and distributed deployments. It is available under the Apache 2.0 license for free self-hosting, plus Qdrant Cloud, a managed service billed hourly on the actual compute and storage resources you provision rather than per query, which many teams find more predictable than usage-metered competitors. The company positions Qdrant as composable vector search infrastructure for production AI, and it has gained significant adoption as a cost-efficient, performant alternative to proprietary options. It competes with Pinecone, Weaviate, Milvus, and Chroma, differentiating on Rust performance, filtering, and transparent resource-based pricing.