Check institutional memory for relevant scars before taking action. Returns matching scars and their lessons. Integrates variant assignment when issue_id provided.

Confirm surfaced scars with APPLYING/N_A/REFUTED decisions and evidence. REQUIRED after recall() before consequential actions. Each recalled scar must be addressed. APPLYING: past-tense evidence of compliance. N_A: explain why scar doesn't apply. REFUTED: acknowledge risk of overriding.

End-of-session scar reflection — the closing counterpart to confirm_scars. Mirrors CODA-1's [Scar Reflection] protocol. Call BEFORE session_close to provide evidence of how each surfaced scar was handled. OBEYED: concrete evidence of compliance (min 15 chars). REFUTED: why it didn't apply + what was done instead (min 30 chars). Session close uses reflections to set execution_successful accurately.

Initialize session, detect agent, load institutional context (last session, recent decisions, open threads). Scars surface on-demand via recall(). DISPLAY: The result includes a pre-formatted 'display' field visible in the tool result. Output the display field verbatim as your response — tool results are collapsed in the CLI.

Re-surface institutional context (threads, decisions) for the current active session without creating a new session. Use mid-session when you need to remember where you left off, after context compaction, or after a long gap. DISPLAY: The result includes a pre-formatted 'display' field visible in the tool result. Output the display field verbatim as your response — tool results are collapsed in the CLI.

Persist session with compliance validation. Two modes: (1) Write closing_reflection and other payload to {gitmem_dir}/closing-payload.json, then call with session_id + close_type. (2) Pass closing_reflection directly as a parameter (simpler). Both work — inline params override file payload. task_completion is auto-generated. DISPLAY: Output the display field verbatim.

Create scar, win, or pattern entry in institutional memory. Frame as 'what we now know' — lead with the factual/architectural discovery, not what went wrong. Good: 'Fine-grained PATs are scoped to one resource owner'. Bad: 'Should have checked PAT type first'.

Log architectural/operational decision to institutional memory

Track scar application for effectiveness measurement

Search institutional memory by query. Unlike recall (which is action-oriented), search is exploration-oriented — returns matching scars/wins/patterns without side effects.

List recent learnings chronologically (like git log). Shows scars, wins, and patterns ordered by creation date.

Generate portable memory payload for sub-agent injection. Formats institutional memory into compact or gate payloads that fit in Task tool prompts.

Capture observations from sub-agents and teammates. The lead agent parses findings from sub-agent responses, then calls this to persist and analyze them. Identifies scar candidates.

List open threads across recent sessions. Shows unresolved work items that carry over between sessions. Use resolve_thread to mark threads as done.

Mark an open thread as resolved. Use thread_id for exact match or text_match for fuzzy matching. Updates session state and .gitmem/threads.json.

Create an open thread to track unresolved work across sessions. Includes semantic dedup: if a similar open thread exists (cosine similarity > 0.85), returns the existing thread instead. Check the 'deduplicated' field in the response.

Promote a suggested thread to an open thread. Takes a suggestion_id from session_start's suggested_threads list and creates a real thread from it.

Dismiss a suggested thread. Incremented dismiss count — suggestions dismissed 3+ times are permanently suppressed.

Triage open threads by lifecycle health. Groups threads as active/cooling/dormant with vitality scores. Use auto_archive=true to archive threads dormant 30+ days. Review and resolve stale threads to keep your thread list healthy.

Show write health for the current session. Reports success/failure rates for all tracked fire-and-forget operations (metrics, cache, triple writes, embeddings, scar usage). Use this to diagnose silent failures.

Session analytics and insights engine. Returns formatted markdown by default. Use format=json for raw data.

gitmem-help - Show available commands with ASCII art header

gitmem-cache-status - Show local search cache status (scar count, age, staleness)

gitmem-cache-health - Compare local cache against remote Supabase (detect out-of-sync)

gitmem-cache-flush - Force reload cache from Supabase (use when out of sync)

Archives a learning (scar/win/pattern) by setting is_active=false and recording archived_at timestamp. Archived learnings are excluded from recall and search results but preserved for audit trail.

Traverse the knowledge graph over institutional memory triples. Answers: 'show me everything connected to this issue', 'what did this agent produce', 'trace this decision back', 'which issues produced the most learnings'. Four lenses: connected_to, produced_by, provenance, stats.

Submit feedback about gitmem — feature requests, bug reports, friction points, or suggestions. Always saved locally to .gitmem/feedback/. If opted in, sent anonymously to improve gitmem. 10/session limit.

Scan a directory of markdown files, chunk them, embed them, and store them in a local doc index for semantic search. Supports incremental indexing: only re-processes changed files. Use search_docs to query the indexed docs.

Search indexed repository documentation using semantic similarity (pro/dev tier) or BM25 keyword search (free tier). Returns relevant chunks with file paths for targeted reading. Index docs first with index_docs.