{
  "schemaVersion": "1.0",
  "item": {
    "slug": "elite-longterm-memory-1-2-3",
    "name": "Elite Longterm Memory 1.2.3",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/itsjustFred/elite-longterm-memory-1-2-3",
    "canonicalUrl": "https://clawhub.ai/itsjustFred/elite-longterm-memory-1-2-3",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/elite-longterm-memory-1-2-3",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=elite-longterm-memory-1-2-3",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "_meta.json",
      "bin/elite-memory.js",
      "package.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/elite-longterm-memory-1-2-3"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/elite-longterm-memory-1-2-3",
    "agentPageUrl": "https://openagent3.xyz/skills/elite-longterm-memory-1-2-3/agent",
    "manifestUrl": "https://openagent3.xyz/skills/elite-longterm-memory-1-2-3/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/elite-longterm-memory-1-2-3/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Elite Longterm Memory 🧠",
        "body": "The ultimate memory system for AI agents. Combines 6 proven approaches into one bulletproof architecture.\n\nNever lose context. Never forget decisions. Never repeat mistakes."
      },
      {
        "title": "Architecture Overview",
        "body": "┌─────────────────────────────────────────────────────────────────┐\n│                    ELITE LONGTERM MEMORY                        │\n├─────────────────────────────────────────────────────────────────┤\n│                                                                 │\n│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐             │\n│  │   HOT RAM   │  │  WARM STORE │  │  COLD STORE │             │\n│  │             │  │             │  │             │             │\n│  │ SESSION-    │  │  LanceDB    │  │  Git-Notes  │             │\n│  │ STATE.md    │  │  Vectors    │  │  Knowledge  │             │\n│  │             │  │             │  │  Graph      │             │\n│  │ (survives   │  │ (semantic   │  │ (permanent  │             │\n│  │  compaction)│  │  search)    │  │  decisions) │             │\n│  └─────────────┘  └─────────────┘  └─────────────┘             │\n│         │                │                │                     │\n│         └────────────────┼────────────────┘                     │\n│                          ▼                                      │\n│                  ┌─────────────┐                                │\n│                  │  MEMORY.md  │  ← Curated long-term           │\n│                  │  + daily/   │    (human-readable)            │\n│                  └─────────────┘                                │\n│                          │                                      │\n│                          ▼                                      │\n│                  ┌─────────────┐                                │\n│                  │ SuperMemory │  ← Cloud backup (optional)     │\n│                  │    API      │                                │\n│                  └─────────────┘                                │\n│                                                                 │\n└─────────────────────────────────────────────────────────────────┘"
      },
      {
        "title": "Layer 1: HOT RAM (SESSION-STATE.md)",
        "body": "From: bulletproof-memory\n\nActive working memory that survives compaction. Write-Ahead Log protocol.\n\n# SESSION-STATE.md — Active Working Memory\n\n## Current Task\n[What we're working on RIGHT NOW]\n\n## Key Context\n- User preference: ...\n- Decision made: ...\n- Blocker: ...\n\n## Pending Actions\n- [ ] ...\n\nRule: Write BEFORE responding. Triggered by user input, not agent memory."
      },
      {
        "title": "Layer 2: WARM STORE (LanceDB Vectors)",
        "body": "From: lancedb-memory\n\nSemantic search across all memories. Auto-recall injects relevant context.\n\n# Auto-recall (happens automatically)\nmemory_recall query=\"project status\" limit=5\n\n# Manual store\nmemory_store text=\"User prefers dark mode\" category=\"preference\" importance=0.9"
      },
      {
        "title": "Layer 3: COLD STORE (Git-Notes Knowledge Graph)",
        "body": "From: git-notes-memory\n\nStructured decisions, learnings, and context. Branch-aware.\n\n# Store a decision (SILENT - never announce)\npython3 memory.py -p $DIR remember '{\"type\":\"decision\",\"content\":\"Use React for frontend\"}' -t tech -i h\n\n# Retrieve context\npython3 memory.py -p $DIR get \"frontend\""
      },
      {
        "title": "Layer 4: CURATED ARCHIVE (MEMORY.md + daily/)",
        "body": "From: OpenClaw native\n\nHuman-readable long-term memory. Daily logs + distilled wisdom.\n\nworkspace/\n├── MEMORY.md              # Curated long-term (the good stuff)\n└── memory/\n    ├── 2026-01-30.md      # Daily log\n    ├── 2026-01-29.md\n    └── topics/            # Topic-specific files"
      },
      {
        "title": "Layer 5: CLOUD BACKUP (SuperMemory) — Optional",
        "body": "From: supermemory\n\nCross-device sync. Chat with your knowledge base.\n\nexport SUPERMEMORY_API_KEY=\"your-key\"\nsupermemory add \"Important context\"\nsupermemory search \"what did we decide about...\""
      },
      {
        "title": "Layer 6: AUTO-EXTRACTION (Mem0) — Recommended",
        "body": "NEW: Automatic fact extraction\n\nMem0 automatically extracts facts from conversations. 80% token reduction.\n\nnpm install mem0ai\nexport MEM0_API_KEY=\"your-key\"\n\nconst { MemoryClient } = require('mem0ai');\nconst client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });\n\n// Conversations auto-extract facts\nawait client.add(messages, { user_id: \"user123\" });\n\n// Retrieve relevant memories\nconst memories = await client.search(query, { user_id: \"user123\" });\n\nBenefits:\n\nAuto-extracts preferences, decisions, facts\nDeduplicates and updates existing memories\n80% reduction in tokens vs raw history\nWorks across sessions automatically"
      },
      {
        "title": "1. Create SESSION-STATE.md (Hot RAM)",
        "body": "cat > SESSION-STATE.md << 'EOF'\n# SESSION-STATE.md — Active Working Memory\n\nThis file is the agent's \"RAM\" — survives compaction, restarts, distractions.\n\n## Current Task\n[None]\n\n## Key Context\n[None yet]\n\n## Pending Actions\n- [ ] None\n\n## Recent Decisions\n[None yet]\n\n---\n*Last updated: [timestamp]*\nEOF"
      },
      {
        "title": "2. Enable LanceDB (Warm Store)",
        "body": "In ~/.openclaw/openclaw.json:\n\n{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"openai\",\n    \"sources\": [\"memory\"],\n    \"minScore\": 0.3,\n    \"maxResults\": 10\n  },\n  \"plugins\": {\n    \"entries\": {\n      \"memory-lancedb\": {\n        \"enabled\": true,\n        \"config\": {\n          \"autoCapture\": false,\n          \"autoRecall\": true,\n          \"captureCategories\": [\"preference\", \"decision\", \"fact\"],\n          \"minImportance\": 0.7\n        }\n      }\n    }\n  }\n}"
      },
      {
        "title": "3. Initialize Git-Notes (Cold Store)",
        "body": "cd ~/clawd\ngit init  # if not already\npython3 skills/git-notes-memory/memory.py -p . sync --start"
      },
      {
        "title": "4. Verify MEMORY.md Structure",
        "body": "# Ensure you have:\n# - MEMORY.md in workspace root\n# - memory/ folder for daily logs\nmkdir -p memory"
      },
      {
        "title": "5. (Optional) Setup SuperMemory",
        "body": "export SUPERMEMORY_API_KEY=\"your-key\"\n# Add to ~/.zshrc for persistence"
      },
      {
        "title": "On Session Start",
        "body": "Read SESSION-STATE.md — this is your hot context\nRun memory_search for relevant prior context\nCheck memory/YYYY-MM-DD.md for recent activity"
      },
      {
        "title": "During Conversation",
        "body": "User gives concrete detail? → Write to SESSION-STATE.md BEFORE responding\nImportant decision made? → Store in Git-Notes (SILENTLY)\nPreference expressed? → memory_store with importance=0.9"
      },
      {
        "title": "On Session End",
        "body": "Update SESSION-STATE.md with final state\nMove significant items to MEMORY.md if worth keeping long-term\nCreate/update daily log in memory/YYYY-MM-DD.md"
      },
      {
        "title": "Memory Hygiene (Weekly)",
        "body": "Review SESSION-STATE.md — archive completed tasks\nCheck LanceDB for junk: memory_recall query=\"*\" limit=50\nClear irrelevant vectors: memory_forget id=<id>\nConsolidate daily logs into MEMORY.md"
      },
      {
        "title": "The WAL Protocol (Critical)",
        "body": "Write-Ahead Log: Write state BEFORE responding, not after.\n\nTriggerActionUser states preferenceWrite to SESSION-STATE.md → then respondUser makes decisionWrite to SESSION-STATE.md → then respondUser gives deadlineWrite to SESSION-STATE.md → then respondUser corrects youWrite to SESSION-STATE.md → then respond\n\nWhy? If you respond first and crash/compact before saving, context is lost. WAL ensures durability."
      },
      {
        "title": "Example Workflow",
        "body": "User: \"Let's use Tailwind for this project, not vanilla CSS\"\n\nAgent (internal):\n1. Write to SESSION-STATE.md: \"Decision: Use Tailwind, not vanilla CSS\"\n2. Store in Git-Notes: decision about CSS framework\n3. memory_store: \"User prefers Tailwind over vanilla CSS\" importance=0.9\n4. THEN respond: \"Got it — Tailwind it is...\""
      },
      {
        "title": "Maintenance Commands",
        "body": "# Audit vector memory\nmemory_recall query=\"*\" limit=50\n\n# Clear all vectors (nuclear option)\nrm -rf ~/.openclaw/memory/lancedb/\nopenclaw gateway restart\n\n# Export Git-Notes\npython3 memory.py -p . export --format json > memories.json\n\n# Check memory health\ndu -sh ~/.openclaw/memory/\nwc -l MEMORY.md\nls -la memory/"
      },
      {
        "title": "Why Memory Fails",
        "body": "Understanding the root causes helps you fix them:\n\nFailure ModeCauseFixForgets everythingmemory_search disabledEnable + add OpenAI keyFiles not loadedAgent skips reading memoryAdd to AGENTS.md rulesFacts not capturedNo auto-extractionUse Mem0 or manual loggingSub-agents isolatedDon't inherit contextPass context in task promptRepeats mistakesLessons not loggedWrite to memory/lessons.md"
      },
      {
        "title": "1. Quick Win: Enable memory_search",
        "body": "If you have an OpenAI key, enable semantic search:\n\nopenclaw configure --section web\n\nThis enables vector search over MEMORY.md + memory/*.md files."
      },
      {
        "title": "2. Recommended: Mem0 Integration",
        "body": "Auto-extract facts from conversations. 80% token reduction.\n\nnpm install mem0ai\n\nconst { MemoryClient } = require('mem0ai');\n\nconst client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });\n\n// Auto-extract and store\nawait client.add([\n  { role: \"user\", content: \"I prefer Tailwind over vanilla CSS\" }\n], { user_id: \"ty\" });\n\n// Retrieve relevant memories\nconst memories = await client.search(\"CSS preferences\", { user_id: \"ty\" });"
      },
      {
        "title": "3. Better File Structure (No Dependencies)",
        "body": "memory/\n├── projects/\n│   ├── strykr.md\n│   └── taska.md\n├── people/\n│   └── contacts.md\n├── decisions/\n│   └── 2026-01.md\n├── lessons/\n│   └── mistakes.md\n└── preferences.md\n\nKeep MEMORY.md as a summary (<5KB), link to detailed files."
      },
      {
        "title": "Immediate Fixes Checklist",
        "body": "ProblemFixForgets preferencesAdd ## Preferences section to MEMORY.mdRepeats mistakesLog every mistake to memory/lessons.mdSub-agents lack contextInclude key context in spawn task promptForgets recent workStrict daily file disciplineMemory search not workingCheck OPENAI_API_KEY is set"
      },
      {
        "title": "Troubleshooting",
        "body": "Agent keeps forgetting mid-conversation:\n→ SESSION-STATE.md not being updated. Check WAL protocol.\n\nIrrelevant memories injected:\n→ Disable autoCapture, increase minImportance threshold.\n\nMemory too large, slow recall:\n→ Run hygiene: clear old vectors, archive daily logs.\n\nGit-Notes not persisting:\n→ Run git notes push to sync with remote.\n\nmemory_search returns nothing:\n→ Check OpenAI API key: echo $OPENAI_API_KEY\n→ Verify memorySearch enabled in openclaw.json"
      },
      {
        "title": "Links",
        "body": "bulletproof-memory: https://clawdhub.com/skills/bulletproof-memory\nlancedb-memory: https://clawdhub.com/skills/lancedb-memory\ngit-notes-memory: https://clawdhub.com/skills/git-notes-memory\nmemory-hygiene: https://clawdhub.com/skills/memory-hygiene\nsupermemory: https://clawdhub.com/skills/supermemory\n\nBuilt by @NextXFrontier — Part of the Next Frontier AI toolkit"
      }
    ],
    "body": "Elite Longterm Memory 🧠\n\nThe ultimate memory system for AI agents. Combines 6 proven approaches into one bulletproof architecture.\n\nNever lose context. Never forget decisions. Never repeat mistakes.\n\nArchitecture Overview\n┌─────────────────────────────────────────────────────────────────┐\n│                    ELITE LONGTERM MEMORY                        │\n├─────────────────────────────────────────────────────────────────┤\n│                                                                 │\n│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐             │\n│  │   HOT RAM   │  │  WARM STORE │  │  COLD STORE │             │\n│  │             │  │             │  │             │             │\n│  │ SESSION-    │  │  LanceDB    │  │  Git-Notes  │             │\n│  │ STATE.md    │  │  Vectors    │  │  Knowledge  │             │\n│  │             │  │             │  │  Graph      │             │\n│  │ (survives   │  │ (semantic   │  │ (permanent  │             │\n│  │  compaction)│  │  search)    │  │  decisions) │             │\n│  └─────────────┘  └─────────────┘  └─────────────┘             │\n│         │                │                │                     │\n│         └────────────────┼────────────────┘                     │\n│                          ▼                                      │\n│                  ┌─────────────┐                                │\n│                  │  MEMORY.md  │  ← Curated long-term           │\n│                  │  + daily/   │    (human-readable)            │\n│                  └─────────────┘                                │\n│                          │                                      │\n│                          ▼                                      │\n│                  ┌─────────────┐                                │\n│                  │ SuperMemory │  ← Cloud backup (optional)     │\n│                  │    API      │                                │\n│                  └─────────────┘                                │\n│                                                                 │\n└─────────────────────────────────────────────────────────────────┘\n\nThe 5 Memory Layers\nLayer 1: HOT RAM (SESSION-STATE.md)\n\nFrom: bulletproof-memory\n\nActive working memory that survives compaction. Write-Ahead Log protocol.\n\n# SESSION-STATE.md — Active Working Memory\n\n## Current Task\n[What we're working on RIGHT NOW]\n\n## Key Context\n- User preference: ...\n- Decision made: ...\n- Blocker: ...\n\n## Pending Actions\n- [ ] ...\n\n\nRule: Write BEFORE responding. Triggered by user input, not agent memory.\n\nLayer 2: WARM STORE (LanceDB Vectors)\n\nFrom: lancedb-memory\n\nSemantic search across all memories. Auto-recall injects relevant context.\n\n# Auto-recall (happens automatically)\nmemory_recall query=\"project status\" limit=5\n\n# Manual store\nmemory_store text=\"User prefers dark mode\" category=\"preference\" importance=0.9\n\nLayer 3: COLD STORE (Git-Notes Knowledge Graph)\n\nFrom: git-notes-memory\n\nStructured decisions, learnings, and context. Branch-aware.\n\n# Store a decision (SILENT - never announce)\npython3 memory.py -p $DIR remember '{\"type\":\"decision\",\"content\":\"Use React for frontend\"}' -t tech -i h\n\n# Retrieve context\npython3 memory.py -p $DIR get \"frontend\"\n\nLayer 4: CURATED ARCHIVE (MEMORY.md + daily/)\n\nFrom: OpenClaw native\n\nHuman-readable long-term memory. Daily logs + distilled wisdom.\n\nworkspace/\n├── MEMORY.md              # Curated long-term (the good stuff)\n└── memory/\n    ├── 2026-01-30.md      # Daily log\n    ├── 2026-01-29.md\n    └── topics/            # Topic-specific files\n\nLayer 5: CLOUD BACKUP (SuperMemory) — Optional\n\nFrom: supermemory\n\nCross-device sync. Chat with your knowledge base.\n\nexport SUPERMEMORY_API_KEY=\"your-key\"\nsupermemory add \"Important context\"\nsupermemory search \"what did we decide about...\"\n\nLayer 6: AUTO-EXTRACTION (Mem0) — Recommended\n\nNEW: Automatic fact extraction\n\nMem0 automatically extracts facts from conversations. 80% token reduction.\n\nnpm install mem0ai\nexport MEM0_API_KEY=\"your-key\"\n\nconst { MemoryClient } = require('mem0ai');\nconst client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });\n\n// Conversations auto-extract facts\nawait client.add(messages, { user_id: \"user123\" });\n\n// Retrieve relevant memories\nconst memories = await client.search(query, { user_id: \"user123\" });\n\n\nBenefits:\n\nAuto-extracts preferences, decisions, facts\nDeduplicates and updates existing memories\n80% reduction in tokens vs raw history\nWorks across sessions automatically\nQuick Setup\n1. Create SESSION-STATE.md (Hot RAM)\ncat > SESSION-STATE.md << 'EOF'\n# SESSION-STATE.md — Active Working Memory\n\nThis file is the agent's \"RAM\" — survives compaction, restarts, distractions.\n\n## Current Task\n[None]\n\n## Key Context\n[None yet]\n\n## Pending Actions\n- [ ] None\n\n## Recent Decisions\n[None yet]\n\n---\n*Last updated: [timestamp]*\nEOF\n\n2. Enable LanceDB (Warm Store)\n\nIn ~/.openclaw/openclaw.json:\n\n{\n  \"memorySearch\": {\n    \"enabled\": true,\n    \"provider\": \"openai\",\n    \"sources\": [\"memory\"],\n    \"minScore\": 0.3,\n    \"maxResults\": 10\n  },\n  \"plugins\": {\n    \"entries\": {\n      \"memory-lancedb\": {\n        \"enabled\": true,\n        \"config\": {\n          \"autoCapture\": false,\n          \"autoRecall\": true,\n          \"captureCategories\": [\"preference\", \"decision\", \"fact\"],\n          \"minImportance\": 0.7\n        }\n      }\n    }\n  }\n}\n\n3. Initialize Git-Notes (Cold Store)\ncd ~/clawd\ngit init  # if not already\npython3 skills/git-notes-memory/memory.py -p . sync --start\n\n4. Verify MEMORY.md Structure\n# Ensure you have:\n# - MEMORY.md in workspace root\n# - memory/ folder for daily logs\nmkdir -p memory\n\n5. (Optional) Setup SuperMemory\nexport SUPERMEMORY_API_KEY=\"your-key\"\n# Add to ~/.zshrc for persistence\n\nAgent Instructions\nOn Session Start\nRead SESSION-STATE.md — this is your hot context\nRun memory_search for relevant prior context\nCheck memory/YYYY-MM-DD.md for recent activity\nDuring Conversation\nUser gives concrete detail? → Write to SESSION-STATE.md BEFORE responding\nImportant decision made? → Store in Git-Notes (SILENTLY)\nPreference expressed? → memory_store with importance=0.9\nOn Session End\nUpdate SESSION-STATE.md with final state\nMove significant items to MEMORY.md if worth keeping long-term\nCreate/update daily log in memory/YYYY-MM-DD.md\nMemory Hygiene (Weekly)\nReview SESSION-STATE.md — archive completed tasks\nCheck LanceDB for junk: memory_recall query=\"*\" limit=50\nClear irrelevant vectors: memory_forget id=<id>\nConsolidate daily logs into MEMORY.md\nThe WAL Protocol (Critical)\n\nWrite-Ahead Log: Write state BEFORE responding, not after.\n\nTrigger\tAction\nUser states preference\tWrite to SESSION-STATE.md → then respond\nUser makes decision\tWrite to SESSION-STATE.md → then respond\nUser gives deadline\tWrite to SESSION-STATE.md → then respond\nUser corrects you\tWrite to SESSION-STATE.md → then respond\n\nWhy? If you respond first and crash/compact before saving, context is lost. WAL ensures durability.\n\nExample Workflow\nUser: \"Let's use Tailwind for this project, not vanilla CSS\"\n\nAgent (internal):\n1. Write to SESSION-STATE.md: \"Decision: Use Tailwind, not vanilla CSS\"\n2. Store in Git-Notes: decision about CSS framework\n3. memory_store: \"User prefers Tailwind over vanilla CSS\" importance=0.9\n4. THEN respond: \"Got it — Tailwind it is...\"\n\nMaintenance Commands\n# Audit vector memory\nmemory_recall query=\"*\" limit=50\n\n# Clear all vectors (nuclear option)\nrm -rf ~/.openclaw/memory/lancedb/\nopenclaw gateway restart\n\n# Export Git-Notes\npython3 memory.py -p . export --format json > memories.json\n\n# Check memory health\ndu -sh ~/.openclaw/memory/\nwc -l MEMORY.md\nls -la memory/\n\nWhy Memory Fails\n\nUnderstanding the root causes helps you fix them:\n\nFailure Mode\tCause\tFix\nForgets everything\tmemory_search disabled\tEnable + add OpenAI key\nFiles not loaded\tAgent skips reading memory\tAdd to AGENTS.md rules\nFacts not captured\tNo auto-extraction\tUse Mem0 or manual logging\nSub-agents isolated\tDon't inherit context\tPass context in task prompt\nRepeats mistakes\tLessons not logged\tWrite to memory/lessons.md\nSolutions (Ranked by Effort)\n1. Quick Win: Enable memory_search\n\nIf you have an OpenAI key, enable semantic search:\n\nopenclaw configure --section web\n\n\nThis enables vector search over MEMORY.md + memory/*.md files.\n\n2. Recommended: Mem0 Integration\n\nAuto-extract facts from conversations. 80% token reduction.\n\nnpm install mem0ai\n\nconst { MemoryClient } = require('mem0ai');\n\nconst client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY });\n\n// Auto-extract and store\nawait client.add([\n  { role: \"user\", content: \"I prefer Tailwind over vanilla CSS\" }\n], { user_id: \"ty\" });\n\n// Retrieve relevant memories\nconst memories = await client.search(\"CSS preferences\", { user_id: \"ty\" });\n\n3. Better File Structure (No Dependencies)\nmemory/\n├── projects/\n│   ├── strykr.md\n│   └── taska.md\n├── people/\n│   └── contacts.md\n├── decisions/\n│   └── 2026-01.md\n├── lessons/\n│   └── mistakes.md\n└── preferences.md\n\n\nKeep MEMORY.md as a summary (<5KB), link to detailed files.\n\nImmediate Fixes Checklist\nProblem\tFix\nForgets preferences\tAdd ## Preferences section to MEMORY.md\nRepeats mistakes\tLog every mistake to memory/lessons.md\nSub-agents lack context\tInclude key context in spawn task prompt\nForgets recent work\tStrict daily file discipline\nMemory search not working\tCheck OPENAI_API_KEY is set\nTroubleshooting\n\nAgent keeps forgetting mid-conversation: → SESSION-STATE.md not being updated. Check WAL protocol.\n\nIrrelevant memories injected: → Disable autoCapture, increase minImportance threshold.\n\nMemory too large, slow recall: → Run hygiene: clear old vectors, archive daily logs.\n\nGit-Notes not persisting: → Run git notes push to sync with remote.\n\nmemory_search returns nothing: → Check OpenAI API key: echo $OPENAI_API_KEY → Verify memorySearch enabled in openclaw.json\n\nLinks\nbulletproof-memory: https://clawdhub.com/skills/bulletproof-memory\nlancedb-memory: https://clawdhub.com/skills/lancedb-memory\ngit-notes-memory: https://clawdhub.com/skills/git-notes-memory\nmemory-hygiene: https://clawdhub.com/skills/memory-hygiene\nsupermemory: https://clawdhub.com/skills/supermemory\n\nBuilt by @NextXFrontier — Part of the Next Frontier AI toolkit"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/itsjustFred/elite-longterm-memory-1-2-3",
    "publisherUrl": "https://clawhub.ai/itsjustFred/elite-longterm-memory-1-2-3",
    "owner": "itsjustFred",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/elite-longterm-memory-1-2-3",
    "downloadUrl": "https://openagent3.xyz/downloads/elite-longterm-memory-1-2-3",
    "agentUrl": "https://openagent3.xyz/skills/elite-longterm-memory-1-2-3/agent",
    "manifestUrl": "https://openagent3.xyz/skills/elite-longterm-memory-1-2-3/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/elite-longterm-memory-1-2-3/agent.md"
  }
}