cuba-memorys: Cuba-Memorys is a Model Context Protocol (MCP) server that gives AI coding assistants long-term persistent memory. It uses a knowledge graph, neuroscience-inspired algorithms like FSRS-6 adaptive decay, Hebbian learning, and dual-strength memory, along with anti-hallucination grounding. The latest version 2.0.0 is a complete Rust rewrite with 12 tools and sub-millisecond performance.; qveris-agent-toolkit: QVeris Agent Toolkit is the open-source client layer for the QVeris capability routing network, giving agents access to 10,000+ real-world capabilities across 15+ categories. It ships a CLI, MCP server, Python SDK, and REST API docs so agents can discover, inspect, invoke, and audit tools through a single protocol. Available for Cursor, Claude Code, OpenCode, and OpenClaw-style skill agents.
Persistent learning from project context: store and retrieve entities, observations, and relations
Agents discovering and invoking real-world APIs without per-integration setup