Stats
Actions
Tags
From openltm
SQLite-backed memory system for storing and retrieving project insights, decisions, and gotchas. Automatically recalls relevant context and supports learn/forget/relate commands.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openltm:ContinuousLearningThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
SQLite-backed memory system at `$CLAUDE_PLUGIN_DATA/openltm.db`. Two tables: `memories` (global learned insights) and `context_items` (per-project goals/decisions/progress/gotchas).
SQLite-backed memory system at $CLAUDE_PLUGIN_DATA/openltm.db. Two tables: memories (global learned insights) and context_items (per-project goals/decisions/progress/gotchas).
| Trigger | Action |
|---|---|
| "Learn this", "Remember this", "Save this pattern" | Run /openltm:memory learn |
| "What do I know about X?", "Any past decisions on Y?" | Run /openltm:memory recall |
| "Forget about X", "That memory is wrong" | Run /openltm:memory forget |
| "X supports Y", "X contradicts Y" | Run /openltm:memory relate |
Recall before non-trivial work and capture genuinely new insights — the goal is automatic retrieval and capture, not a call on every turn. Skip recall for trivial one-liners; skip learn for facts already derivable from the code or git history.
Example 1 — User asks about past architecture:
User: "What's our caching strategy?" LLM: Calls
recall(query="caching strategy architecture")→ uses results in response.
Example 2 — User discovers a gotcha:
User: "Don't use npm in this project, it's broken with our setup." LLM: Calls
learn(content="Don't use npm - broken with our setup", category="gotcha", importance=4)→ confirms stored.
Example 3 — User starts new feature:
User: "Add auth to the API." LLM: Calls
recall(query="auth")+context(project="api")→ incorporates prior decisions.
/openltm:memory learn — Store an insight in memories table. Dedup-safe (reinforces on repeat)./openltm:memory recall [query] — FTS5 search with tag/category/project filters./openltm:memory forget <id> — Delete by ID. CASCADE removes relations. Irreversible./openltm:memory relate <src> <tgt> <type> — Link memories. Types: supports|contradicts|refines|depends_on|related_to|supersedes.context-*.md files needed.SkillSearch('continuouslearning memory reference') → MemoryReference.mdSkillSearch('continuouslearning hook integration') → HookIntegration.mdSkillSearch('continuouslearning context items') → ContextItems.mdnpx claudepluginhub rohirik/openltm --plugin openltmPROACTIVELY query Forgetful MCP (mcp__forgetful__* tools) when starting work on any project, when user references past decisions or patterns, when implementing features that may have been solved before, or when needing context about preferences. Save important decisions, patterns, and architectural insights to memory.
Persists learnings into a 5-layer memory hierarchy (CLAUDE.md files, memory/MEMORY.md) and consolidates by pruning outdated entries and promoting recurring patterns. Triggers on 'extract learnings', 'remember', 'dream'.