Mem-on-the-Go
Universal agent memory system built on RuVector. Multiple reinforcement learning algorithms, hybrid BM25 and vector search with Reciprocal Rank Fusion, GNN multi-head attention for better recall, and auto-selecting backends. Runs anywhere with zero setup: browser WASM, Node.js, edge functions, fully offline. Fast native search with Rust and SIMD acceleration. Self-learning steadily improves retrieval quality without manual tuning.
RustWASMHNSWReinforcement LearningGNNTypeScriptAgentDBRuVectorMCPSelf-Learning