AgentRecall-MCP: AgentRecall is a learning loop for AI agents that provides persistent, compounding memory. It captures corrections automatically, surfaces past insights across projects, and uses a five-layer memory pyramid with Ebbinghaus decay and Bayesian feedback. Zero cloud, all local markdown files.; holaOS: holaOS is an agent environment built for long-horizon work, continuity, and self-evolution. It provides agents with a structured operating system including runtime, memory, tools, apps, and durable state, enabling them to operate continuously, evolve over time, and remain inspectable across different runs.
Maintain context across AI agent sessions (Claude Code, Cursor, etc.)
Building agents that perform complex, multi-step tasks over extended periods