hmem-context

You can recall past design decisions by loading the most relevant memory context from long-term storage on demand. This skill identifies and retrieves specific past patterns or lessons to inform current answers, reducing manual search time.

You need long-term memory context when a question relies on past design decisions, code patterns, or specific lessons not present in the immediate project brief. Loading this memory ensures the AI has the exact historical details required for accurate responses.

To retrieve relevant code patterns, the skill performs stepwise memory searches against long-term storage. It filters the results to the top 3 most relevant matches and formats them for direct AI context loading.

Yes, memory lookup results can be filtered to present only the top 3 most relevant memories. This filtering ensures the AI receives precise, targeted historical context without being overwhelmed by unrelated information.

The best way to fetch exact memory nodes is through on-demand retrieval from long-term memory storage. This approach fetches precise memory context based on the current question, directly supporting accurate decision-making.

Yes, this memory lookup approach works independently without external dependencies or components. It directly accesses long-term storage to load and format the necessary memory context for your AI.