// Detect breakthrough moments, durable lessons, and decisions worth preserving. Suggest distillation sparingly, then store high-value knowledge as atomic memories.
| name | distill-memory |
| description | Detect breakthrough moments, durable lessons, and decisions worth preserving. Suggest distillation sparingly, then store high-value knowledge as atomic memories. |
Save proactively when the conversation produces a decision, preference, plan, procedure, learning, or important context. Do not wait to be asked.
memory_add when the insight is genuinely new and MCP tools are available. Otherwise use nmem --json m add.memory_update when available. Otherwise use nmem m update <id> ... instead of creating a duplicate.Prefer atomic, standalone memories with strong titles and structured meaning. Focus on what was learned or decided, not routine chatter.
Read the user's daily Working Memory briefing at session start or when recent priorities matter. This gives Gemini CLI cross-tool continuity without bloating the main prompt.
Search the user's personal knowledge base when past insights would improve the response. Trigger proactively for continuity, recurring bugs, design rationale, and remembered workflows.
Save a concise Gemini CLI handoff summary only when the user explicitly asks. This is intentionally separate from full thread-save, which should use the native Gemini session importer.
Save the real Gemini CLI session to Nowledge Mem only when the user explicitly asks. This uses Gemini's native transcript-backed importer rather than a summary-only fallback.