MCP.Market

Gitmem MCP server

by gitmem-dev·io.github.gitmem-dev/gitmem·v1.2.1·9 stars

Persistent institutional memory for AI coding agents. Memory that compounds.

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

9 stars988 downloads/wk

Reviews

Write one

Nobody has reviewed Gitmem yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Gitmem tools (79, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • absorb_observations

    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.

  • analyze

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

  • archive_learning

    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.

  • cleanup_threads

    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.

  • confirm_scars

    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.

  • create_decisionwrite action

    Log architectural/operational decision to institutional memory

  • create_learningwrite action

    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'.

  • create_threadwrite action

    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.

  • dismiss_suggestion

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

  • get_transcript

    Retrieve a session transcript from storage

  • gitmem-al

    gitmem-al (archive_learning) - Archive a scar/win/pattern (sets is_active=false)

  • gitmem-analyze

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

  • gitmem-ao

    gitmem-ao (absorb_observations) - Capture sub-agent/teammate observations

  • gitmem-cache-flush

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

  • gitmem-cache-health

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

  • gitmem-cache-status

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

  • gitmem-cd

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

  • gitmem-cl

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

  • gitmem-cleanup

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

  • gitmem-cs

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

  • gitmem-ct

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

  • gitmem-ds

    gitmem-ds (dismiss_suggestion) - Dismiss a suggested thread

  • gitmem-graph

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

  • gitmem-gt

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

  • gitmem-health

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

  • gitmem-help

    gitmem-help - Show available commands with ASCII art header

  • gitmem-log

    gitmem-log (log) - List recent learnings chronologically

  • gitmem-lt

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

  • gitmem-pc

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

  • gitmem-ps

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

  • gitmem-r

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

  • gitmem-rs

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

  • gitmem-rsb

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

  • gitmem-rt

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

  • gitmem-sc

    gitmem-sc (session_close) - Close session with compliance validation. IMPORTANT: Write all heavy payload data (closing_reflection, task_completion, human_corrections, scars_to_record, open_threads, decisions, learnings_created) to {gitmem_dir}/closing-payload.json BEFORE calling this tool — gitmem_dir is from session_start. Only pass session_id and close_type inline. DISPLAY: The result includes a

  • gitmem-search

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

  • gitmem-sr

    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

    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

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

  • gitmem-stx

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

  • gm-absorb

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

  • gm-analyze

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

  • gm-archive

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

  • gm-cache-f

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

  • gm-cache-h

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

  • gm-cache-s

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

  • gm-cleanup

    gm-cleanup (cleanup_threads) - Triage threads by health

  • gm-close

    gm-close (session_close) - Close a GitMem session. IMPORTANT: Write all heavy payload data (closing_reflection, task_completion, human_corrections, scars_to_record, open_threads, decisions, learnings_created) to {gitmem_dir}/closing-payload.json BEFORE calling this tool — gitmem_dir is from session_start. Only pass session_id and close_type inline. DISPLAY: The result includes a pre-formatted 'dis

  • gm-confirm

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

  • gm-dismiss

    gm-dismiss (dismiss_suggestion) - Dismiss a suggested thread

  • gm-graph

    gm-graph (graph_traverse) - Traverse knowledge graph

  • gm-health

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

  • gm-log

    gm-log (log) - List recent learnings chronologically

  • gm-open

    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

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

  • gm-promote

    gm-promote (promote_suggestion) - Promote a suggested thread

  • gm-refresh

    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

    gm-resolve (resolve_thread) - Resolve a thread

  • gm-scar

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

  • gm-search

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

  • gm-stx

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

  • gm-thread-new

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

  • gm-threads

    gm-threads (list_threads) - List open threads

  • graph_traverse

    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.

  • health

    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.

  • list_threads

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

  • log

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

  • prepare_context

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

  • promote_suggestion

    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.

  • recall

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

  • record_scar_usage

    Track scar application for effectiveness measurement

  • record_scar_usage_batch

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

  • resolve_thread

    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_transcript

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

  • search

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

  • search_transcripts

    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.

  • session_close

    Persist session with compliance validation. IMPORTANT: Before calling this tool, write all heavy payload data (closing_reflection, human_corrections, scars_to_record, open_threads, decisions, learnings_created) to {gitmem_dir}/closing-payload.json using your file write tool — the gitmem_dir path is returned by session_start (also shown in session start display as 'Payload path'). Then call this to

  • session_refresh

    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 th

  • session_start

    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.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings
  • Code scan191 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Gitmem compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
79
the typical server has 7
Tools that change things
4%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
9
more than 87% of 28,688 servers
Downloads a week
988
more than 95% of 12,191 servers with a package

What its tools let an agent do: 74 read · 4 create · 1 delete

Install Gitmem in Claude Code, Cursor or VS Code

Runs npx -y gitmem-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add gitmem -- npx -y gitmem-mcp
Add to Cursor

What the publisher says

From the Gitmem repository's README, as published. We do not edit it. Read it on GitHub

= 18" />

Documentation · npm · Getting Started · Tool Reference

GitMem is an MCP server that gives your AI coding agent persistent learning memory across agent sessions. It remembers mistakes (scars), successes (wins), and decisions — so your agent learns from experience instead of starting from scratch every time.

What's MCP? Model Context Protocol is how AI coding tools connect to external capabilities. GitMem is an MCP server — install it once and your agent gains persistent memory.

Works with Claude Code, Cursor, VS Code (Copilot), Windsurf, and any MCP-compatible client.

Quick Start

npx gitmem-mcp init

One command. The wizard auto-detects your IDE and sets up everything:

  • .gitmem/ directory with starter scars
  • MCP server config (.mcp.json, .vscode/mcp.json, .cursor/mcp.json, etc.)
  • Instructions file (CLAUDE.md, .cursorrules, .windsurfrules, .github/copilot-instructions.md)
  • Lifecycle hooks (where supported)
  • .gitignore updated

Already have existing config? The wizard merges without destroying anything. Re-running is safe.

npx gitmem-mcp init --yes                # Non-interactive
npx gitmem-mcp init --dry-run            # Preview changes
npx gitmem-mcp init --client vscode      # Force specific client

How It Works

recall  -->  work  -->  learn  -->  close  -->  recall  -->  ...
  1. Recall — Before acting, the agent checks memory for relevant lessons from past sessions
  2. Work — The agent does the task, applying past lessons automatically
  3. Learn — Mistakes become scars, successes become wins, strategies become patterns
  4. Close — Session reflection persists context for next time

Every scar includes counter-arguments — reasons why someone might reasonably ignore it. This prevents memory from becoming a pile of rigid rules.

What Gets Remembered

Key Features

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Gitmem: common questions

Is Gitmem MCP server safe?
Mostly: it is graded B (82/100). Read the Gitmem safety report
How do I install Gitmem?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Gitmem need an API key?
Yes. The registry entry asks for SUPABASE_SERVICE_ROLE_KEY.
Is Gitmem maintained?
The last commit was 42 days ago (2026-09-23). The latest release is v1.2.1.
What can I use instead of Gitmem?
Servers from other publishers that do the same job: Deja Vu MCP server, State Memory MCP server and Knowl MCP server. Compare all Gitmem alternatives.
How does Gitmem compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 79 (the typical server has 7); tools that change things 4% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Gitmem

Same job from other publishers: the closest match first, then the best rated.

All Gitmem alternatives →
  • Deja Vu
    deja-vu: local memory over the session histories of forty-three coding agents.
    A
  • State Memory MCP
    Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.
    A
  • Knowl
    Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.
    A