Qdrant
Open-source vector search engine and database written in Rust for AI retrieval, search, and recommendation applications.
📍 Germany 🇩🇪, Berlin
Product overview
Qdrant is a Berlin-based company that builds an open-source vector database designed for AI applications. Written entirely in Rust, the engine stores and searches high-dimensional vectors, the mathematical representations that AI models use to understand text, images, audio, and other unstructured data. Developers use it to power semantic search, recommendation systems, RAG (retrieval-augmented generation) pipelines, and AI agent memory. Founded in 2021 by Andre Zayarni and Andrey Vasnetsov, the company raised $50 million in its latest round, bringing total funding to around $88 million. Investors include Spark Capital, Unusual Ventures, 42CAP, and IBB Ventures. The product started as an open-source GitHub project that quickly attracted developer interest, leading the founders to build a commercial company around it. Qdrant differentiates itself through composable vector search, giving developers fine-grained control over how indexing, filtering, and retrieval work in production. The engine supports hybrid search combining dense and sparse vectors, advanced filtering applied during HNSW traversal, and binary quantization that reduces memory consumption by up to 32x. Deployment options include Qdrant Cloud (managed, on AWS, GCP, or Azure), Hybrid Cloud (bring your own Kubernetes), Private Cloud (air-gapped), and Qdrant Edge for on-device search. KEY FEATURES: - Open-source vector database written in Rust with sub-millisecond latency - Hybrid search combining dense vectors, sparse vectors, and keyword search - Binary quantization reducing memory usage by up to 32x - Flexible deployment: managed cloud, hybrid, private, and edge options - GPU-accelerated vector indexing for real-time AI applications