{
  "schemaVersion": "1.0",
  "item": {
    "slug": "session-memory",
    "name": "Session Memory",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/swaylq/session-memory",
    "canonicalUrl": "https://clawhub.ai/swaylq/session-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/session-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=session-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "package.json",
      "scripts/consolidate.sh",
      "scripts/context.sh",
      "scripts/daily.sh"
    ],
    "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",
      "slug": "session-memory",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T16:32:59.605Z",
      "expiresAt": "2026-05-10T16:32:59.605Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=session-memory",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=session-memory",
        "contentDisposition": "attachment; filename=\"session-memory-2.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "session-memory"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/session-memory"
    },
    "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/session-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/session-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/session-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/session-memory/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": "Session Memory 🧠 v2.0",
        "body": "Persistent memory for AI agents. Save what matters, recall what's relevant, consolidate what you've learned.\n\nv2.0: relevance-scored search, importance levels, session context loader, consolidation, export/import, stats, edit/delete."
      },
      {
        "title": "Quick Start",
        "body": "# Save a memory (with optional importance)\nMEMORY_IMPORTANCE=high ./scripts/save.sh \"decision\" \"Chose Postgres over SQLite for scale\"\n\n# Recall with relevance scoring\n./scripts/recall.sh \"database\" --limit 5\n\n# Load session context (startup)\n./scripts/context.sh --days 3\n\n# Consolidate by topic\n./scripts/consolidate.sh --since 2026-01-01\n\n# Stats\n./scripts/stats.sh"
      },
      {
        "title": "save.sh — Save a Memory",
        "body": "./scripts/save.sh \"topic\" \"content\" [tags...]\n\nEnvDefaultDescriptionAGENT_MEMORY_DIR~/.agent-memoryStorage directoryMEMORY_IMPORTANCEnormallow / normal / high / critical\n\n# Basic save\n./scripts/save.sh \"insight\" \"Users prefer dark mode 3:1\" ui design\n\n# High importance\nMEMORY_IMPORTANCE=high ./scripts/save.sh \"decision\" \"Migrated to TypeScript\" refactor\n\n# Critical (always surfaces in context.sh)\nMEMORY_IMPORTANCE=critical ./scripts/save.sh \"credential\" \"API key rotated, new one in vault\""
      },
      {
        "title": "recall.sh — Search Memories",
        "body": "./scripts/recall.sh \"query\" [--json] [--limit N] [--topic T] [--importance I] [--since YYYY-MM-DD]\n\nFeatures:\n\nMulti-keyword AND search — all words must match\nRelevance scoring — based on word match ratio + importance + recency\nFilters — by topic, importance level, date range\n\n./scripts/recall.sh \"database migration\"\n./scripts/recall.sh \"API\" --topic decision --limit 20\n./scripts/recall.sh \"deploy\" --since 2026-03-01 --json\n./scripts/recall.sh \"error\" --importance high"
      },
      {
        "title": "context.sh — Session Startup Loader",
        "body": "./scripts/context.sh [--days N] [--limit N] [--json]\n\nLoads the most relevant memories for a new session:\n\nRecent memories (last N days, default 3)\nHigh/critical importance items regardless of age\nSorted by importance then recency\nGrouped by date\n\n# Quick context\n./scripts/context.sh\n\n# Wider window\n./scripts/context.sh --days 7 --limit 30\n\n# For programmatic use\n./scripts/context.sh --json"
      },
      {
        "title": "daily.sh — Day View",
        "body": "./scripts/daily.sh [YYYY-MM-DD] [--json]"
      },
      {
        "title": "topics.sh — Topic Index",
        "body": "./scripts/topics.sh [--json]"
      },
      {
        "title": "consolidate.sh — Topic Consolidation",
        "body": "./scripts/consolidate.sh [--since YYYY-MM-DD] [--topic T] [--json]\n\nGroups all memories by topic, showing counts, date ranges, top tags, and latest entries. Useful for periodic review."
      },
      {
        "title": "stats.sh — Memory Statistics",
        "body": "./scripts/stats.sh [--json]\n\nShows: total entries, date range, entries/day average, storage size, topic breakdown, importance distribution."
      },
      {
        "title": "edit.sh — Edit or Delete",
        "body": "./scripts/edit.sh <timestamp_ms> --content \"new content\"\n./scripts/edit.sh <timestamp_ms> --topic \"new topic\"\n./scripts/edit.sh <timestamp_ms> --importance critical\n./scripts/edit.sh <timestamp_ms> --delete"
      },
      {
        "title": "export.sh — Export Memories",
        "body": "./scripts/export.sh [-o backup.json] [--since YYYY-MM-DD] [--topic T]"
      },
      {
        "title": "import.sh — Import Memories",
        "body": "./scripts/import.sh backup.json [--dry-run]\n\nDeduplicates by timestamp — safe to run multiple times."
      },
      {
        "title": "prune.sh — Archive Old Memories",
        "body": "./scripts/prune.sh [days]\n\nMoves memories older than N days (default: 30) to archive/."
      },
      {
        "title": "Storage",
        "body": "~/.agent-memory/\n├── 2026/\n│   ├── 01/\n│   │   ├── 15.jsonl\n│   │   └── 16.jsonl\n│   └── 02/\n│       └── 01.jsonl\n└── archive/          # Pruned memories\n\nEach line is a JSON object:\n\n{\"ts\":1706793600000,\"topic\":\"decision\",\"content\":\"Chose X because Y\",\"tags\":[\"project\"],\"importance\":\"high\"}"
      },
      {
        "title": "Importance Levels",
        "body": "LevelWhen to UseBehaviorlowBackground info, minor notesOnly found via searchnormalStandard memoriesShown in daily viewhighKey decisions, insightsAlways in session contextcriticalCredentials, blockers, urgentAlways in session context, top priority"
      },
      {
        "title": "Recommended Workflow",
        "body": "# Session start\n./scripts/context.sh\n\n# During work — save important things\n./scripts/save.sh \"decision\" \"...\"\nMEMORY_IMPORTANCE=high ./scripts/save.sh \"insight\" \"...\"\n\n# End of session\n./scripts/save.sh \"summary\" \"Today: did X, decided Y, next step Z\"\n\n# Weekly review\n./scripts/consolidate.sh --since $(date -u -d '7 days ago' +%Y-%m-%d)\n./scripts/stats.sh\n\n# Monthly maintenance\n./scripts/prune.sh 60\n./scripts/export.sh -o backup-$(date +%Y%m).json\n\nCreated by Voidborne 🔹"
      }
    ],
    "body": "Session Memory 🧠 v2.0\n\nPersistent memory for AI agents. Save what matters, recall what's relevant, consolidate what you've learned.\n\nv2.0: relevance-scored search, importance levels, session context loader, consolidation, export/import, stats, edit/delete.\n\nQuick Start\n# Save a memory (with optional importance)\nMEMORY_IMPORTANCE=high ./scripts/save.sh \"decision\" \"Chose Postgres over SQLite for scale\"\n\n# Recall with relevance scoring\n./scripts/recall.sh \"database\" --limit 5\n\n# Load session context (startup)\n./scripts/context.sh --days 3\n\n# Consolidate by topic\n./scripts/consolidate.sh --since 2026-01-01\n\n# Stats\n./scripts/stats.sh\n\nCommands\nsave.sh — Save a Memory\n./scripts/save.sh \"topic\" \"content\" [tags...]\n\nEnv\tDefault\tDescription\nAGENT_MEMORY_DIR\t~/.agent-memory\tStorage directory\nMEMORY_IMPORTANCE\tnormal\tlow / normal / high / critical\n# Basic save\n./scripts/save.sh \"insight\" \"Users prefer dark mode 3:1\" ui design\n\n# High importance\nMEMORY_IMPORTANCE=high ./scripts/save.sh \"decision\" \"Migrated to TypeScript\" refactor\n\n# Critical (always surfaces in context.sh)\nMEMORY_IMPORTANCE=critical ./scripts/save.sh \"credential\" \"API key rotated, new one in vault\"\n\nrecall.sh — Search Memories\n./scripts/recall.sh \"query\" [--json] [--limit N] [--topic T] [--importance I] [--since YYYY-MM-DD]\n\n\nFeatures:\n\nMulti-keyword AND search — all words must match\nRelevance scoring — based on word match ratio + importance + recency\nFilters — by topic, importance level, date range\n./scripts/recall.sh \"database migration\"\n./scripts/recall.sh \"API\" --topic decision --limit 20\n./scripts/recall.sh \"deploy\" --since 2026-03-01 --json\n./scripts/recall.sh \"error\" --importance high\n\ncontext.sh — Session Startup Loader\n./scripts/context.sh [--days N] [--limit N] [--json]\n\n\nLoads the most relevant memories for a new session:\n\nRecent memories (last N days, default 3)\nHigh/critical importance items regardless of age\nSorted by importance then recency\nGrouped by date\n# Quick context\n./scripts/context.sh\n\n# Wider window\n./scripts/context.sh --days 7 --limit 30\n\n# For programmatic use\n./scripts/context.sh --json\n\ndaily.sh — Day View\n./scripts/daily.sh [YYYY-MM-DD] [--json]\n\ntopics.sh — Topic Index\n./scripts/topics.sh [--json]\n\nconsolidate.sh — Topic Consolidation\n./scripts/consolidate.sh [--since YYYY-MM-DD] [--topic T] [--json]\n\n\nGroups all memories by topic, showing counts, date ranges, top tags, and latest entries. Useful for periodic review.\n\nstats.sh — Memory Statistics\n./scripts/stats.sh [--json]\n\n\nShows: total entries, date range, entries/day average, storage size, topic breakdown, importance distribution.\n\nedit.sh — Edit or Delete\n./scripts/edit.sh <timestamp_ms> --content \"new content\"\n./scripts/edit.sh <timestamp_ms> --topic \"new topic\"\n./scripts/edit.sh <timestamp_ms> --importance critical\n./scripts/edit.sh <timestamp_ms> --delete\n\nexport.sh — Export Memories\n./scripts/export.sh [-o backup.json] [--since YYYY-MM-DD] [--topic T]\n\nimport.sh — Import Memories\n./scripts/import.sh backup.json [--dry-run]\n\n\nDeduplicates by timestamp — safe to run multiple times.\n\nprune.sh — Archive Old Memories\n./scripts/prune.sh [days]\n\n\nMoves memories older than N days (default: 30) to archive/.\n\nStorage\n~/.agent-memory/\n├── 2026/\n│   ├── 01/\n│   │   ├── 15.jsonl\n│   │   └── 16.jsonl\n│   └── 02/\n│       └── 01.jsonl\n└── archive/          # Pruned memories\n\n\nEach line is a JSON object:\n\n{\"ts\":1706793600000,\"topic\":\"decision\",\"content\":\"Chose X because Y\",\"tags\":[\"project\"],\"importance\":\"high\"}\n\nImportance Levels\nLevel\tWhen to Use\tBehavior\nlow\tBackground info, minor notes\tOnly found via search\nnormal\tStandard memories\tShown in daily view\nhigh\tKey decisions, insights\tAlways in session context\ncritical\tCredentials, blockers, urgent\tAlways in session context, top priority\nRecommended Workflow\n# Session start\n./scripts/context.sh\n\n# During work — save important things\n./scripts/save.sh \"decision\" \"...\"\nMEMORY_IMPORTANCE=high ./scripts/save.sh \"insight\" \"...\"\n\n# End of session\n./scripts/save.sh \"summary\" \"Today: did X, decided Y, next step Z\"\n\n# Weekly review\n./scripts/consolidate.sh --since $(date -u -d '7 days ago' +%Y-%m-%d)\n./scripts/stats.sh\n\n# Monthly maintenance\n./scripts/prune.sh 60\n./scripts/export.sh -o backup-$(date +%Y%m).json\n\n\nCreated by Voidborne 🔹"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/swaylq/session-memory",
    "publisherUrl": "https://clawhub.ai/swaylq/session-memory",
    "owner": "swaylq",
    "version": "2.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/session-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/session-memory",
    "agentUrl": "https://openagent3.xyz/skills/session-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/session-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/session-memory/agent.md"
  }
}