Back to directory

RuVector

A Rust-native substrate for fast local decisions and persistent AI-agent memory, combining local semantic embeddings, vector retrieval, graph relationships and feedback-based learning without a database server or API key.

RuVector

RuVector is a Rust substrate for fast local decisions and cross-session agent memory, combining local semantic embeddings, persistent vector retrieval, graph relationships, explicit feedback learning and memory lifecycle controls, with optional shared memory. Retrieval runs locally by default, and hosted services remain optional, keeping a separate data boundary.

A separate decision-engine package turns text into typed choice, score or abstention decisions using local embeddings and native decision heads with a WASM fallback, intended for bounded tasks such as ticket routing or urgency assessment where a full model call is unnecessary; it is not enabled by installing the root package alone. Memory can be stored and recalled from the command line or embedded directly in a Node.js application with no external database or API key required, and reopening the same storage path recovers previously stored vectors, metadata and configuration.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.