Gitmem

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

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

gitmem-cd (create_decision) - Log architectural/operational decision

gitmem-cl (create_learning) - Create scar/win/pattern. Frame as 'what we now know' — factual discovery, not self-criticism.

gitmem-cleanup (cleanup_threads) - Triage threads by lifecycle health

gitmem-cs (confirm_scars) - Confirm recalled scars with APPLYING/N_A/REFUTED decisions

gitmem-ct (create_thread) - Create an open thread with semantic dedup (cosine > 0.85 blocks duplicates)

gitmem-ds (dismiss_suggestion) - Dismiss a suggested thread

gitmem-fb (contribute_feedback) - Submit feedback about gitmem

gitmem-graph (graph_traverse) - Traverse knowledge graph over institutional memory triples

gitmem-gt (get_transcript) - Retrieve session transcript from storage

gitmem-health (health) - Show write health for fire-and-forget operations this session

gitmem-help - Show available commands with ASCII art header

Alias for index_docs. Scan a directory of markdown files and index them for semantic search.

gitmem-log (log) - List recent learnings chronologically

gitmem-lt (list_threads) - List open threads across sessions

gitmem-pc (prepare_context) - Generate portable memory payload for sub-agent injection

gitmem-ps (promote_suggestion) - Promote a suggested thread to an open thread

gitmem-r (recall) - Check institutional memory for relevant scars before taking action

gitmem-rf (reflect_scars) - End-of-session scar reflection (OBEYED/REFUTED with evidence)

gitmem-rs (record_scar_usage) - Track scar application for effectiveness measurement

gitmem-rsb (record_scar_usage_batch) - Track multiple scars in batch (reduces latency)

gitmem-rt (resolve_thread) - Mark a thread as resolved

gitmem-sc (session_close) - Close session. Two modes: (1) Write payload to closing-payload.json first, or (2) pass closing_reflection directly as param. Both work.

Alias for search_docs. Search indexed repository documentation.

gitmem-search (search) - Search institutional memory by query (exploration, no side effects)

gitmem-sr (session_refresh) - Refresh institutional context for the active session without creating a new session. DISPLAY: The result includes a pre-formatted 'display' field. Output the display field verbatim as your response — tool results are collapsed in the CLI.

gitmem-ss (session_start) - Initialize session with institutional context. DISPLAY: The result includes a pre-formatted 'display' field. Output the display field verbatim as your response — tool results are collapsed in the CLI.

gitmem-st (save_transcript) - Save session transcript to storage

gitmem-stx (search_transcripts) - Semantic search over transcript chunks

gm-absorb (absorb_observations) - Capture sub-agent observations

gm-analyze (analyze) - Session analytics. Returns formatted markdown by default.

gm-archive (archive_learning) - Archive a scar/win/pattern

gm-cache-f (cache_flush) - Force reload cache from Supabase

gm-cache-h (cache_health) - Compare local cache against remote Supabase (detect out-of-sync)

gm-cache-s (cache_status) - Show local search cache status (scar count, age, staleness)

gm-cleanup (cleanup_threads) - Triage threads by health

gm-close (session_close) - Close session. Pass closing_reflection directly or write to closing-payload.json first.

gm-confirm (confirm_scars) - Confirm recalled scars with APPLYING/N_A/REFUTED

gm-dismiss (dismiss_suggestion) - Dismiss a suggested thread

gm-feedback (contribute_feedback) - Submit feedback about gitmem

gm-graph (graph_traverse) - Traverse knowledge graph

gm-health (health) - Show write health for fire-and-forget operations

gm-log (log) - List recent learnings chronologically

gm-open (session_start) - Open a GitMem session and load institutional context. DISPLAY: The result includes a pre-formatted 'display' field. Output the display field verbatim as your response — tool results are collapsed in the CLI.

gm-pc (prepare_context) - Generate portable memory payload for sub-agents

gm-promote (promote_suggestion) - Promote a suggested thread

gm-reflect (reflect_scars) - End-of-session scar reflection

gm-refresh (session_refresh) - Refresh context for the active session without creating a new one. DISPLAY: The result includes a pre-formatted 'display' field. Output the display field verbatim as your response — tool results are collapsed in the CLI.

gm-resolve (resolve_thread) - Resolve a thread

gm-scar (create_learning) - Create a scar/win/pattern. Frame as 'what we now know' — factual discovery, not self-criticism.

gm-search (search) - Search institutional memory by query

gm-stx (search_transcripts) - Semantic search over transcript chunks

gm-thread-new (create_thread) - Create an open thread with semantic dedup

gm-threads (list_threads) - List open threads

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.

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.

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.

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

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.

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.

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

Track scar application for effectiveness measurement

Track multiple scar applications in a single batch operation (reduces session close latency)

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.

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.

Save full session transcript to storage for training data and post-mortems

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

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.

Semantic search over session transcript chunks. Generates embedding for query and calls match_transcript_chunks RPC to find relevant conversation fragments across all indexed sessions.

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.

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.

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.