ruvnet/RuVector

The vector database that gets smarter the more you use it — and now ships as a cognitive container.

Most vector databases are static — they store embeddings and search them. That's it. RuVector is different: it learns from every query, runs LLMs locally, scales horizontally, boots as a Linux microservice from a single file, and costs nothing to operate.

One package. Everything included: vector search, graph queries, GNN learning, distributed clustering, local LLMs, 40+ attention mechanisms, cognitive containers (RVF — self-booting .rvf files with eBPF, witness chains, and COW branching), and WASM support.

Think of it as: Pinecone + Neo4j + PyTorch + llama.cpp + postgres + etcd + Docker — in one Rust package.

The RVF cognitive container is the Docker part: a single .rvf file that stores vectors, ships models, boots as a Linux microservice in 125 ms, accelerates queries via eBPF, branches like Git at cluster granularity, and proves every operation through a cryptographic witness chain — all without external dependencies.

Over time, frequently-accessed paths get reinforced, making common queries faster and more accurate.