npm:nan-forget

IMPORTANT: You MUST call this tool proactively whenever you learn a decision, preference, fact, or context worth remembering across sessions. Do NOT w

IMPORTANT: Call this DURING the conversation whenever you encounter a topic that may have prior context — auth, deployment, testing, architecture, too

Get a specific memory by its ID. Use when you have a memory ID from search results and need the full content.

Update an existing memory. Use to correct, refine, or add tags to a memory.

Archive a memory (soft delete). The memory is never truly deleted — just hidden from search. Use when a decision is reversed or information is outdate

Consolidate aging memories into compact long-term entries. Clusters related memories by topic, summarizes them (LLM if available, deterministic fallba

Run garbage collection on memories. Archives decayed (unused) memories, removes expired ones, deduplicates near-identical entries, and syncs MEMORY.md

Show memory statistics: active/archived counts, breakdown by type and project. Use to check memory health and understand what you remember.

Check if nan-forget services are running (Ollama, REST API). Call this at the start of each session to verify everything is ready. If services are dow

Start all nan-forget services (Ollama, REST API). Only call this after the user confirms they want services started. Starts Ollama and the REST API.

IMPORTANT: Call this ONCE at the start of every session. Lightweight handshake — checks if services are running, reports how many memories are availab

Call this BEFORE telling the user a task is done. Captures the full problem→solution context as a structured memory for future sessions. Use after: bu

Compress local .md memory files that have been persisted to the DB. Replaces redundant files with minimal stubs to keep context window clean. Call aft