What problem does it solve? AI agents lose all context about a user when a chat session ends, forcing users to repeat their preferences, project details, and goals in every new conversation. This Skill gives the agent a persistent long-term memory store backed by the Knowledge Base (KB) CLI so knowledge survives across sessions and restarts. ## Core Features & Use Cases - Dedicated Memory Projects: Automatically creates a per-agent, per-user memory project (e.g., opencode_schalk_memory) at session startup. - Selective Memory Storage: Saves stable preferences, long-term projects, goals, and workflows as categorized entries (preference, note, decision, goal) while excluding credentials and sensitive data. - Contextual Recall: Queries the memory project mid-conversation with commands like kb ask to retrieve relevant preferences and project context. - Use Case: A developer tells the agent they prefer VS Code with Vim keybindings and are building a Vulkan rendering engine; months later, in a fresh session, the agent recalls both facts without being reminded. ## Quick Start Ask the agent to remember your preferred editor and current long-term project so it can recall them in future sessions.
