/ الدليل / الملعب / claude-mem
● مجتمع thedotmack ⚡ فوري

claude-mem

بواسطة thedotmack · thedotmack/claude-mem

claude-mem captures every Claude Code session, compresses it with AI into a searchable memory, and injects only the relevant bits into future sessions.

claude-mem is a plugin/skill hybrid for Claude Code (also Gemini CLI and OpenCode). Five lifecycle hooks observe everything your agent does; an AI compression pass distills sessions into structured observations; a SQLite + Chroma vector store powers semantic recall. You search memory with the mem-search skill, and a local web viewer at localhost:37777 shows the memory stream in real time. Privacy controls via <private> tags keep secrets out. The biggest win: no more 'remind me what we decided last Tuesday' at the start of every session.

لماذا تستخدمه

الميزات الأساسية

عرض مباشر

كيف يبدو في الممارسة

claude-mem-skill.replay ▶ جاهز
0/0

التثبيت

اختر العميل

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

افتح Claude Desktop → Settings → Developer → Edit Config. أعد التشغيل بعد الحفظ.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

يستخدم Cursor نفس مخطط mcpServers مثل Claude Desktop. إعدادات المشروع أولى من الإعدادات العامة.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

انقر على أيقونة MCP Servers في شريط Cline الجانبي، ثم "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "claude-mem-skill": {
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  }
}

نفس الصيغة مثل Claude Desktop. أعد تشغيل Windsurf لتطبيق التغييرات.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "claude-mem-skill",
      "command": "npx",
      "args": [
        "claude-mem",
        "install"
      ]
    }
  ]
}

يستخدم Continue مصفوفة من كائنات الخادم بدلاً من خريطة.

~/.config/zed/settings.json
{
  "context_servers": {
    "claude-mem-skill": {
      "command": {
        "path": "npx",
        "args": [
          "claude-mem",
          "install"
        ]
      }
    }
  }
}

أضف إلى context_servers. يعيد Zed التحميل تلقائيًا عند الحفظ.

claude mcp add claude-mem-skill -- npx claude-mem install

أمر من سطر واحد. تحقق باستخدام claude mcp list. احذف باستخدام claude mcp remove.

حالات الاستخدام

استخدامات عملية: claude-mem

Resume a multi-week project without re-briefing Claude every morning

👤 Engineers on long-running features or research ⏱ ~5 min beginner

متى تستخدمه: You spend the first 10 minutes of every session re-explaining context that Claude had yesterday.

المتطلبات الأساسية
  • Claude Code installed — npm install -g @anthropic-ai/claude-code
  • claude-mem installed — npx claude-mem install (registers hooks in ~/.claude)
الخطوات
  1. Work normally
    Just use Claude Code. claude-mem is passive — hooks capture events automatically.✓ تم النسخ
    → localhost:37777 shows the memory stream updating as you work
  2. Start tomorrow's session
    Where did we leave off on the migration branch?✓ تم النسخ
    → Claude recalls concrete facts + cites observation IDs
  3. Correct misremembering
    That's wrong about the DB schema — we decided to keep the v1 field. Mark that observation as corrected.✓ تم النسخ
    → mem-search writes a correction; future recall prioritizes it

النتيجة: Sessions feel continuous. The re-briefing ritual disappears.

المزالق
  • Memory recalls stale facts after you change course — Explicitly mark corrections; mem-search respects recency and overrides
  • Sensitive code snippets get captured — Wrap them in <private>...</private> tags; hooks skip private blocks
اجمعها مع: filesystem

Turn individual sessions into team knowledge without writing docs

👤 Team leads; ICs who avoid writing postmortems ⏱ ~10 min intermediate

متى تستخدمه: You solve a gnarly bug, explain the fix to Claude, and want that explanation findable next month without writing a README.

الخطوات
  1. Narrate your fix
    Walk me through why the deadlock happened and the fix you just landed. Be complete — future me might read this.✓ تم النسخ
    → Claude writes a narrative; compression captures it
  2. Tag the memory
    Tag this observation with 'db-deadlock-2026-04' and 'billing-cluster'.✓ تم النسخ
    → Tags stored on the observation
  3. Recall later
    A month later: 'We've got another deadlock in billing — pull any prior notes.'✓ تم النسخ
    → The April note surfaces first

النتيجة: Lightweight knowledge base that grows by itself.

المزالق
  • Memory gets noisy as months pass — Use mem-search --prune on low-signal old sessions; Endless Mode (beta) handles this automatically
اجمعها مع: memory

Keep customer data and secrets out of memory captures

👤 Anyone working with sensitive data ⏱ ~15 min intermediate

متى تستخدمه: You work on code that touches PII or secrets and can't let them land in a local vector store.

الخطوات
  1. Wrap sensitive blocks
    Write me the sample data with real test records wrapped in <private> tags so claude-mem doesn't capture the values.✓ تم النسخ
    → Private blocks are in the transcript but not in the memory store
  2. Verify
    Open localhost:37777 and check today's stream. Confirm no records from the <private> block appear.✓ تم النسخ
    → Private content absent
  3. Add repo-wide policy
    Update CLAUDE.md: 'Always wrap real customer data in <private>'.✓ تم النسخ
    → CLAUDE.md updated; future sessions inherit

النتيجة: Memory is useful without being a data-leak surface.

المزالق
  • Forgetting to tag sensitive content — Make it a pre-commit / hook convention; claude-mem can enforce prompts that remind on detection

التركيبات

اجمعها مع خوادم MCP أخرى لتحقيق نتائج x10

claude-mem-skill + filesystem

Memory recalls the file you edited, filesystem re-reads it

Pull from mem-search the last file we edited in the billing refactor; then read it and continue where we left off.✓ تم النسخ
claude-mem-skill + serena

Memory supplies the intent; Serena supplies the current code state

Memory says we're renaming ChargeService → BillingService; use Serena to finish the rename.✓ تم النسخ
claude-mem-skill + github

Cross-reference memory with real PR state

Memory says we opened a PR yesterday; use GitHub MCP to get its current status and review comments.✓ تم النسخ

الأدوات

ما يوفره هذا الـ MCP

الأداةالمدخلاتمتى تستدعيهاالتكلفة
mem-search (skill) query: str, limit?: int, since?: date Any time you'd ask Claude to 'remember' — full-text and semantic search over your history free (local SQLite + embedding model)
mem-compress (hook) session transcript Automatic — runs at session end; rarely invoked manually small Claude call per session
web viewer URL http://localhost:37777 Debug what's being captured; check privacy filters free

التكلفة والحدود

تكلفة التشغيل

حصة API
Local SQLite + Chroma vectors; embedding model bundled
الرموز لكل استدعاء
Small — observations are already compressed
التكلفة المالية
Free (MIT)
نصيحة
Compression calls use your Claude API key; set a monthly budget in the claude-mem config if you chat a lot

الأمان

الصلاحيات والأسرار ونطاق الأثر

تخزين بيانات الاعتماد: None for the tool itself; compression uses your existing Claude API key
نقل البيانات الخارجي: Compression calls go to Anthropic (your account); nothing else leaves your machine
لا تمنح أبدًا: Uploading the SQLite/Chroma store off-device without review — it contains transcripts

استكشاف الأخطاء

الأخطاء الشائعة وحلولها

Web viewer at localhost:37777 won't load

Check the hook is running: ps aux | grep claude-mem. Reinstall with npx claude-mem install if it's absent.

تحقق: curl -I http://localhost:37777
Recall returns nothing useful

First few sessions are cold; memory gets better after ~10 sessions as patterns emerge. Also check that hooks are actually firing (see viewer).

تحقق: Open viewer during a session; events should stream in real time
Compression calls are expensive

Lower compression depth in config or use Endless Mode (beta) which is cheaper per session

تحقق: Check Anthropic usage dashboard for attribution
<private> content still shows up

Tag must be on its own lines; inline <private>…</private> in the middle of a sentence isn't parsed. Use block form.

تحقق: Reproduce and inspect the stored observation in the viewer

البدائل

claude-mem مقابل البدائل

البديلمتى تستخدمهاالمقايضة
Memory MCPYou want explicit, user-controlled memory writes — not passive captureYou do the memory-saving yourself; less ambient, less magic
Serena memoryYour use case is code-focused and you'd rather have per-project notes than transcript compressionNo session-stream capture; more project-level
Just take notesYou prefer explicit, human-curated notesNo automation; discipline-dependent

المزيد

الموارد

📖 اقرأ ملف README الرسمي على GitHub

🐙 تصفح القضايا المفتوحة

🔍 تصفح أكثر من 400 خادم MCP و Skills