Mem-on-the-Go
Universal Agent Memory System
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.
خط أنابيب طوبولوجيا النظام
اسحب للاستكشافClick any node to explore details. Multiple RL algorithms, auto-selecting backends.
Agents forget. Every session starts cold, every debugging run re-discovers the same patterns, every code review loses context the moment the process exits. Mem-on-the-Go fixes that. A universal memory system that travels with the agent — browser, Node.js, edge function, fully offline — with zero setup and no API keys.
Built on RuVector, the system automatically selects the highest-performance backend available. Native Rust with SIMD acceleration delivers fast search latency and high query throughput when available. Drop down to a lightweight WASM runtime in the browser and it still works, entirely client-side, with the bundled all-MiniLM-L6-v2 model generating embeddings without touching a server.
Several reinforcement learning algorithms run continuously: Q-Learning, SARSA, DQN, PPO, Actor-Critic, Policy Gradient, Decision Transformer, MCTS, and Model-Based RL. They train together through contrastive learning with InfoNCE loss and hard negative mining, steadily improving retrieval quality over time. LoRA adapters handle fine-tuning efficiently. EWC++ prevents catastrophic forgetting of patterns the system already learned.
Hybrid search combines BM25 keyword matching with HNSW vector similarity through Reciprocal Rank Fusion, exact term matches and semantic understanding working together. A GNN with multi-head attention reranks candidates for better recall. SONA auto-selects the right attention strategy per query, fast enough to stay invisible.
The .rvf cognitive container format bundles index, embeddings, learned RL state, and graph structure into a single portable file. Agent trajectory tracking captures real behavior — debugging sessions, code reviews, research workflows — and distills it into retrieval patterns the system actually improves from. The agent learns from itself.