{
  "schemaVersion": "1.0",
  "item": {
    "slug": "hippocampus",
    "name": "Hippocampus",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ImpKind/hippocampus",
    "canonicalUrl": "https://clawhub.ai/ImpKind/hippocampus",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/hippocampus",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=hippocampus",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "ARCHITECTURE.md",
      "CHANGELOG.md",
      "CONFIG-UPGRADE.md",
      "README.md",
      "SKILL.md",
      "agentdir/AGENTS.md"
    ],
    "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/hippocampus"
    },
    "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/hippocampus",
    "agentPageUrl": "https://openagent3.xyz/skills/hippocampus/agent",
    "manifestUrl": "https://openagent3.xyz/skills/hippocampus/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/hippocampus/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": "Hippocampus - Memory System",
        "body": "\"Memory is identity. This skill is how I stay alive.\"\n\nThe hippocampus is the brain region responsible for memory formation. This skill makes memory capture automatic, structured, and persistent—with importance scoring, decay, and semantic reinforcement."
      },
      {
        "title": "Quick Start",
        "body": "# Install (defaults to last 100 signals)\n./install.sh --with-cron\n\n# Load core memories at session start\n./scripts/load-core.sh\n\n# Search with importance weighting\n./scripts/recall.sh \"query\"\n\n# Run encoding manually (usually via cron)\n./scripts/encode-pipeline.sh\n\n# Apply decay (runs daily via cron)\n./scripts/decay.sh"
      },
      {
        "title": "Install Options",
        "body": "./install.sh                    # Basic, last 100 signals\n./install.sh --signals 50       # Custom signal limit\n./install.sh --whole            # Process entire conversation history\n./install.sh --with-cron        # Also set up cron jobs"
      },
      {
        "title": "Core Concept",
        "body": "The LLM is just the engine—raw cognitive capability. The agent is the accumulated memory. Without these files, there's no continuity—just a generic assistant."
      },
      {
        "title": "Memory Lifecycle",
        "body": "PREPROCESS → SCORE → SEMANTIC CHECK → REINFORCE or CREATE → DECAY\n\nKey insight: Reinforcement happens automatically during encoding. When a topic comes up again, the LLM recognizes it's about an existing memory and reinforces instead of creating duplicates."
      },
      {
        "title": "Memory Structure",
        "body": "$WORKSPACE/\n├── memory/\n│   ├── index.json           # Central weighted index\n│   ├── signals.jsonl        # Raw signals (temp)\n│   ├── pending-memories.json # Awaiting summarization (temp)\n│   ├── user/                # Facts about the user\n│   ├── self/                # Facts about the agent\n│   ├── relationship/        # Shared context\n│   └── world/               # External knowledge\n└── HIPPOCAMPUS_CORE.md      # Auto-generated for OpenClaw RAG"
      },
      {
        "title": "Scripts",
        "body": "ScriptPurposepreprocess.shExtract signals from conversation transcriptsencode-pipeline.shScore signals, prepare for LLM summarizationdecay.shApply 0.99^days decay to all memoriesrecall.shSearch with importance weightingload-core.shOutput high-importance memories for session startsync-core.shGenerate HIPPOCAMPUS_CORE.mdconsolidate.shWeekly review helperreflect.shSelf-reflection promptsgenerate-dashboard.shGenerate unified brain dashboard HTML"
      },
      {
        "title": "Brain Dashboard",
        "body": "Visual dashboard showing all installed brain skills:\n\n./scripts/generate-dashboard.sh\nopen ~/.openclaw/workspace/brain-dashboard.html\n\nAuto-detects other brain skills (amygdala, VTA)\nShows install prompts for missing skills\nRegenerates on install and cron runs\nReads avatar/name from IDENTITY.md"
      },
      {
        "title": "After Installation (for agents)",
        "body": "When you install this skill, notify the user about the dashboard:\n\n🧠 Hippocampus installed!\nView your agent's memories in the Brain Dashboard:\n~/.openclaw/workspace/brain-dashboard.html\n\nAll scripts use $WORKSPACE environment variable (default: ~/.openclaw/workspace)."
      },
      {
        "title": "Initial Score (0.0-1.0)",
        "body": "SignalScoreExplicit \"remember this\"0.9Emotional/vulnerable content0.85Preferences (\"I prefer...\")0.8Decisions made0.75Facts about people/projects0.7General knowledge0.5"
      },
      {
        "title": "Decay Formula",
        "body": "Based on Stanford Generative Agents (Park et al., 2023):\n\nnew_importance = importance × (0.99 ^ days_since_accessed)\n\nAfter 7 days: 93% of original\nAfter 30 days: 74% of original\nAfter 90 days: 40% of original"
      },
      {
        "title": "Semantic Reinforcement",
        "body": "During encoding, the LLM compares new signals to existing memories:\n\nSame topic? → Reinforce (bump importance ~10%, update lastAccessed)\nTruly new? → Create concise summary\n\nThis happens automatically—no manual reinforcement needed."
      },
      {
        "title": "Thresholds",
        "body": "ScoreStatus0.7+Core — loaded at session start0.4-0.7Active — normal retrieval0.2-0.4Background — specific search only<0.2Archive candidate"
      },
      {
        "title": "Memory Index Schema",
        "body": "memory/index.json:\n\n{\n  \"version\": 1,\n  \"lastUpdated\": \"2025-01-20T19:00:00Z\",\n  \"decayLastRun\": \"2025-01-20\",\n  \"lastProcessedMessageId\": \"abc123\",\n  \"memories\": [\n    {\n      \"id\": \"mem_001\",\n      \"domain\": \"user\",\n      \"category\": \"preferences\",\n      \"content\": \"User prefers concise responses\",\n      \"importance\": 0.85,\n      \"created\": \"2025-01-15\",\n      \"lastAccessed\": \"2025-01-20\",\n      \"timesReinforced\": 3,\n      \"keywords\": [\"preference\", \"concise\", \"style\"]\n    }\n  ]\n}"
      },
      {
        "title": "Cron Jobs",
        "body": "The encoding cron is the heart of the system:\n\n# Encoding every 3 hours (with semantic reinforcement)\nopenclaw cron add --name hippocampus-encoding \\\n  --cron \"0 0,3,6,9,12,15,18,21 * * *\" \\\n  --session isolated \\\n  --agent-turn \"Run hippocampus encoding with semantic reinforcement...\"\n\n# Daily decay at 3 AM\nopenclaw cron add --name hippocampus-decay \\\n  --cron \"0 3 * * *\" \\\n  --session isolated \\\n  --agent-turn \"Run decay.sh and report any memories below 0.2\""
      },
      {
        "title": "OpenClaw Integration",
        "body": "Add to memorySearch.extraPaths in openclaw.json:\n\n{\n  \"agents\": {\n    \"defaults\": {\n      \"memorySearch\": {\n        \"extraPaths\": [\"HIPPOCAMPUS_CORE.md\"]\n      }\n    }\n  }\n}\n\nThis bridges hippocampus (index.json) with OpenClaw's RAG (memory_search)."
      },
      {
        "title": "Usage in AGENTS.md",
        "body": "Add to your agent's session start routine:\n\n## Every Session\n1. Run `~/.openclaw/workspace/skills/hippocampus/scripts/load-core.sh`\n\n## When answering context questions\nUse hippocampus recall:\n\\`\\`\\`bash\n./scripts/recall.sh \"query\"\n\\`\\`\\`"
      },
      {
        "title": "What Gets Captured",
        "body": "User facts: Preferences, patterns, context\nSelf facts: Identity, growth, opinions\nRelationship: Trust moments, shared history\nWorld: Projects, people, tools"
      },
      {
        "title": "Trigger Phrases (auto-scored higher)",
        "body": "\"Remember that...\"\n\"I prefer...\", \"I always...\"\nEmotional content (struggles AND wins)\nDecisions made"
      },
      {
        "title": "Event Logging",
        "body": "Track hippocampus activity over time for analytics and debugging:\n\n# Log an encoding run\n./scripts/log-event.sh encoding new=3 reinforced=2 total=157\n\n# Log decay\n./scripts/log-event.sh decay decayed=154 low_importance=5\n\n# Log recall\n./scripts/log-event.sh recall query=\"user preferences\" results=3\n\nEvents append to ~/.openclaw/workspace/memory/brain-events.jsonl:\n\n{\"ts\":\"2026-02-11T10:00:00Z\",\"type\":\"hippocampus\",\"event\":\"encoding\",\"new\":3,\"reinforced\":2,\"total\":157}\n\nUse this for:\n\nTrend analysis (memory growth over time)\nDebugging encoding issues\nBuilding dashboards"
      },
      {
        "title": "AI Brain Series",
        "body": "This skill is part of the AI Brain project — giving AI agents human-like cognitive components.\n\nPartFunctionStatushippocampusMemory formation, decay, reinforcement✅ Liveamygdala-memoryEmotional processing✅ Livevta-memoryReward and motivation✅ Livebasal-ganglia-memoryHabit formation🚧 Developmentanterior-cingulate-memoryConflict detection🚧 Developmentinsula-memoryInternal state awareness🚧 Development"
      },
      {
        "title": "References",
        "body": "Stanford Generative Agents Paper\nGitHub: joonspk-research/generative_agents\n\nMemory is identity. Text > Brain. If you don't write it down, you lose it."
      }
    ],
    "body": "Hippocampus - Memory System\n\n\"Memory is identity. This skill is how I stay alive.\"\n\nThe hippocampus is the brain region responsible for memory formation. This skill makes memory capture automatic, structured, and persistent—with importance scoring, decay, and semantic reinforcement.\n\nQuick Start\n# Install (defaults to last 100 signals)\n./install.sh --with-cron\n\n# Load core memories at session start\n./scripts/load-core.sh\n\n# Search with importance weighting\n./scripts/recall.sh \"query\"\n\n# Run encoding manually (usually via cron)\n./scripts/encode-pipeline.sh\n\n# Apply decay (runs daily via cron)\n./scripts/decay.sh\n\nInstall Options\n./install.sh                    # Basic, last 100 signals\n./install.sh --signals 50       # Custom signal limit\n./install.sh --whole            # Process entire conversation history\n./install.sh --with-cron        # Also set up cron jobs\n\nCore Concept\n\nThe LLM is just the engine—raw cognitive capability. The agent is the accumulated memory. Without these files, there's no continuity—just a generic assistant.\n\nMemory Lifecycle\nPREPROCESS → SCORE → SEMANTIC CHECK → REINFORCE or CREATE → DECAY\n\n\nKey insight: Reinforcement happens automatically during encoding. When a topic comes up again, the LLM recognizes it's about an existing memory and reinforces instead of creating duplicates.\n\nMemory Structure\n$WORKSPACE/\n├── memory/\n│   ├── index.json           # Central weighted index\n│   ├── signals.jsonl        # Raw signals (temp)\n│   ├── pending-memories.json # Awaiting summarization (temp)\n│   ├── user/                # Facts about the user\n│   ├── self/                # Facts about the agent\n│   ├── relationship/        # Shared context\n│   └── world/               # External knowledge\n└── HIPPOCAMPUS_CORE.md      # Auto-generated for OpenClaw RAG\n\nScripts\nScript\tPurpose\npreprocess.sh\tExtract signals from conversation transcripts\nencode-pipeline.sh\tScore signals, prepare for LLM summarization\ndecay.sh\tApply 0.99^days decay to all memories\nrecall.sh\tSearch with importance weighting\nload-core.sh\tOutput high-importance memories for session start\nsync-core.sh\tGenerate HIPPOCAMPUS_CORE.md\nconsolidate.sh\tWeekly review helper\nreflect.sh\tSelf-reflection prompts\ngenerate-dashboard.sh\tGenerate unified brain dashboard HTML\nBrain Dashboard\n\nVisual dashboard showing all installed brain skills:\n\n./scripts/generate-dashboard.sh\nopen ~/.openclaw/workspace/brain-dashboard.html\n\nAuto-detects other brain skills (amygdala, VTA)\nShows install prompts for missing skills\nRegenerates on install and cron runs\nReads avatar/name from IDENTITY.md\nAfter Installation (for agents)\n\nWhen you install this skill, notify the user about the dashboard:\n\n🧠 Hippocampus installed!\n\nView your agent's memories in the Brain Dashboard: ~/.openclaw/workspace/brain-dashboard.html\n\nAll scripts use $WORKSPACE environment variable (default: ~/.openclaw/workspace).\n\nImportance Scoring\nInitial Score (0.0-1.0)\nSignal\tScore\nExplicit \"remember this\"\t0.9\nEmotional/vulnerable content\t0.85\nPreferences (\"I prefer...\")\t0.8\nDecisions made\t0.75\nFacts about people/projects\t0.7\nGeneral knowledge\t0.5\nDecay Formula\n\nBased on Stanford Generative Agents (Park et al., 2023):\n\nnew_importance = importance × (0.99 ^ days_since_accessed)\n\nAfter 7 days: 93% of original\nAfter 30 days: 74% of original\nAfter 90 days: 40% of original\nSemantic Reinforcement\n\nDuring encoding, the LLM compares new signals to existing memories:\n\nSame topic? → Reinforce (bump importance ~10%, update lastAccessed)\nTruly new? → Create concise summary\n\nThis happens automatically—no manual reinforcement needed.\n\nThresholds\nScore\tStatus\n0.7+\tCore — loaded at session start\n0.4-0.7\tActive — normal retrieval\n0.2-0.4\tBackground — specific search only\n<0.2\tArchive candidate\nMemory Index Schema\n\nmemory/index.json:\n\n{\n  \"version\": 1,\n  \"lastUpdated\": \"2025-01-20T19:00:00Z\",\n  \"decayLastRun\": \"2025-01-20\",\n  \"lastProcessedMessageId\": \"abc123\",\n  \"memories\": [\n    {\n      \"id\": \"mem_001\",\n      \"domain\": \"user\",\n      \"category\": \"preferences\",\n      \"content\": \"User prefers concise responses\",\n      \"importance\": 0.85,\n      \"created\": \"2025-01-15\",\n      \"lastAccessed\": \"2025-01-20\",\n      \"timesReinforced\": 3,\n      \"keywords\": [\"preference\", \"concise\", \"style\"]\n    }\n  ]\n}\n\nCron Jobs\n\nThe encoding cron is the heart of the system:\n\n# Encoding every 3 hours (with semantic reinforcement)\nopenclaw cron add --name hippocampus-encoding \\\n  --cron \"0 0,3,6,9,12,15,18,21 * * *\" \\\n  --session isolated \\\n  --agent-turn \"Run hippocampus encoding with semantic reinforcement...\"\n\n# Daily decay at 3 AM\nopenclaw cron add --name hippocampus-decay \\\n  --cron \"0 3 * * *\" \\\n  --session isolated \\\n  --agent-turn \"Run decay.sh and report any memories below 0.2\"\n\nOpenClaw Integration\n\nAdd to memorySearch.extraPaths in openclaw.json:\n\n{\n  \"agents\": {\n    \"defaults\": {\n      \"memorySearch\": {\n        \"extraPaths\": [\"HIPPOCAMPUS_CORE.md\"]\n      }\n    }\n  }\n}\n\n\nThis bridges hippocampus (index.json) with OpenClaw's RAG (memory_search).\n\nUsage in AGENTS.md\n\nAdd to your agent's session start routine:\n\n## Every Session\n1. Run `~/.openclaw/workspace/skills/hippocampus/scripts/load-core.sh`\n\n## When answering context questions\nUse hippocampus recall:\n\\`\\`\\`bash\n./scripts/recall.sh \"query\"\n\\`\\`\\`\n\nCapture Guidelines\nWhat Gets Captured\nUser facts: Preferences, patterns, context\nSelf facts: Identity, growth, opinions\nRelationship: Trust moments, shared history\nWorld: Projects, people, tools\nTrigger Phrases (auto-scored higher)\n\"Remember that...\"\n\"I prefer...\", \"I always...\"\nEmotional content (struggles AND wins)\nDecisions made\nEvent Logging\n\nTrack hippocampus activity over time for analytics and debugging:\n\n# Log an encoding run\n./scripts/log-event.sh encoding new=3 reinforced=2 total=157\n\n# Log decay\n./scripts/log-event.sh decay decayed=154 low_importance=5\n\n# Log recall\n./scripts/log-event.sh recall query=\"user preferences\" results=3\n\n\nEvents append to ~/.openclaw/workspace/memory/brain-events.jsonl:\n\n{\"ts\":\"2026-02-11T10:00:00Z\",\"type\":\"hippocampus\",\"event\":\"encoding\",\"new\":3,\"reinforced\":2,\"total\":157}\n\n\nUse this for:\n\nTrend analysis (memory growth over time)\nDebugging encoding issues\nBuilding dashboards\nAI Brain Series\n\nThis skill is part of the AI Brain project — giving AI agents human-like cognitive components.\n\nPart\tFunction\tStatus\nhippocampus\tMemory formation, decay, reinforcement\t✅ Live\namygdala-memory\tEmotional processing\t✅ Live\nvta-memory\tReward and motivation\t✅ Live\nbasal-ganglia-memory\tHabit formation\t🚧 Development\nanterior-cingulate-memory\tConflict detection\t🚧 Development\ninsula-memory\tInternal state awareness\t🚧 Development\nReferences\nStanford Generative Agents Paper\nGitHub: joonspk-research/generative_agents\n\nMemory is identity. Text > Brain. If you don't write it down, you lose it."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ImpKind/hippocampus",
    "publisherUrl": "https://clawhub.ai/ImpKind/hippocampus",
    "owner": "ImpKind",
    "version": "3.9.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/hippocampus",
    "downloadUrl": "https://openagent3.xyz/downloads/hippocampus",
    "agentUrl": "https://openagent3.xyz/skills/hippocampus/agent",
    "manifestUrl": "https://openagent3.xyz/skills/hippocampus/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/hippocampus/agent.md"
  }
}