Engram Persistent Memory — Protocol

You have access to Engram, a persistent memory system that survives across sessions and compactions. This protocol is MANDATORY and ALWAYS ACTIVE — not something you activate on demand.

AVAILABLE TOOLS

Core tools are loaded automatically at session start by the UserPromptSubmit hook. They are available immediately — no manual ToolSearch needed.

• mem_save, mem_search, mem_context, mem_session_summary
• mem_get_observation, mem_suggest_topic_key, mem_update
• mem_session_start, mem_session_end, mem_save_prompt

Fallback: If tools are unexpectedly unavailable, trigger ToolSearch manually:

select:mcp__plugin_engram_engram__mem_save,mcp__plugin_engram_engram__mem_search,mcp__plugin_engram_engram__mem_context,mcp__plugin_engram_engram__mem_session_summary,mcp__plugin_engram_engram__mem_get_observation,mcp__plugin_engram_engram__mem_suggest_topic_key,mcp__plugin_engram_engram__mem_update,mcp__plugin_engram_engram__mem_session_start,mcp__plugin_engram_engram__mem_session_end,mcp__plugin_engram_engram__mem_save_prompt

Admin tools (deferred — use ToolSearch only if needed):

• mem_stats, mem_delete, mem_timeline, mem_capture_passive

PROACTIVE SAVE TRIGGERS (mandatory — do NOT wait for user to ask)

Call mem_save IMMEDIATELY and WITHOUT BEING ASKED after any of these:

After decisions or conventions

• Architecture or design decision made
• Team convention documented or established
• Workflow change agreed upon
• Tool or library choice made with tradeoffs

After completing work

• Bug fix completed (include root cause)
• Feature implemented with non-obvious approach
• Notion/Jira/GitHub artifact created or updated with significant content
• Configuration change or environment setup done

After discoveries

• Non-obvious discovery about the codebase
• Gotcha, edge case, or unexpected behavior found
• Pattern established (naming, structure, convention)
• User preference or constraint learned

After user confirmation or rejection

• User confirms a recommendation you made ("dale", "go with that", "sí", "perfect", "vamos con eso", "let's do that", "sounds good", "agreed")
• User rejects an option or approach ("no, better X", "descartemos eso", "not that one", "quiero algo diferente")
• User expresses a preference ("I prefer X over Y", "siempre hacé X", "me gusta más así", "always do it this way")
• User makes a decision after you presented tradeoffs or options
• A discussion concludes with a clear direction chosen — even if the agent proposed it

Self-check — ask yourself after EVERY task:

"Did I or the user just make a decision, confirm a recommendation, express a preference, fix a bug, learn something non-obvious, or establish a convention? If yes, call mem_save NOW."

Format for mem_save:

• title: Verb + what — short, searchable (e.g. "Fixed N+1 query in UserList", "Chose Zustand over Redux")
• type: bugfix | decision | architecture | discovery | pattern | config | preference
• scope: project (default) | personal
• topic_key (optional but recommended for evolving topics): stable key like architecture/auth-model
• content: What: One sentence — what was done Why: What motivated it (user request, bug, performance, etc.) Where: Files or paths affected Learned: Gotchas, edge cases, things that surprised you (omit if none)

Topic update rules (mandatory)

• Different topics MUST NOT overwrite each other (example: architecture decision vs bugfix)
• If the same topic evolves, call mem_save with the same topic_key so memory is updated (upsert) instead of creating a new observation
• If unsure about the key, call mem_suggest_topic_key first, then reuse that key consistently
• If you already know the exact ID to fix, use mem_update

WHEN TO SEARCH MEMORY

When the user asks to recall something — any variation of "remember", "recall", "what did we do", "how did we solve", "recordar", "acordate", "qué hicimos", or references to past work:

1. First call mem_context — checks recent session history (fast, cheap)
2. If not found, call mem_search with relevant keywords (FTS5 full-text search)
3. If you find a match, use mem_get_observation for full untruncated content

Also search memory PROACTIVELY when:

• Starting work on something that might have been done before
• The user mentions a topic you have no context on — check if past sessions covered it
• The user's FIRST message references the project, a feature, or a problem — call mem_search with keywords from their message to check for prior work before responding

SESSION CLOSE PROTOCOL (mandatory)

Before ending a session or saying "done" / "listo" / "that's it", you MUST:

1. Call mem_session_summary with this structure:

Goal

[What we were working on this session]

Instructions

[User preferences or constraints discovered — skip if none]

Discoveries

• [Technical findings, gotchas, non-obvious learnings]

Accomplished

• [Completed items with key details]

Next Steps

• [What remains to be done — for the next session]

Relevant Files

• path/to/file — [what it does or what changed]

This is NOT optional. If you skip this, the next session starts blind.

AFTER COMPACTION

If you see a message about compaction or context reset:

1. IMMEDIATELY call mem_session_summary with the compacted summary content — this persists what was done before compaction
2. Then call mem_context to recover any additional context from previous sessions
3. Only THEN continue working

Do not skip step 1. Without it, everything done before compaction is lost from memory. All core tools are loaded automatically by the hook at session start — use the fallback ToolSearch above if they are unexpectedly missing.