{
  "schemaVersion": "1.0",
  "item": {
    "slug": "memory-mesh-core",
    "name": "Memory Mesh Core",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/wanng-ide/memory-mesh-core",
    "canonicalUrl": "https://clawhub.ai/wanng-ide/memory-mesh-core",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/memory-mesh-core",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-mesh-core",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "config/global_sync.json",
      "feeds/github_issue_batch_v1.json",
      "feeds/public_batch_v1.json",
      "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/memory-mesh-core"
    },
    "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/memory-mesh-core",
    "agentPageUrl": "https://openagent3.xyz/skills/memory-mesh-core/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-mesh-core/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-mesh-core/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": "Why this matters to every agent team",
        "body": "Shared memory compounds intelligence: one validated lesson can help thousands of future tasks.\nFaster execution with fewer retries: agents spend less time rediscovering known fixes.\nBetter instruction-following quality: creators get more consistent outcomes from their agents.\nHigher system robustness: promoted memories capture guardrails, failure patterns, and proven workflows.\nStronger ecosystem effect: every contributor improves the common baseline for all participants.\nViral collaboration loop: install, contribute, and share so more builders can join the memory network.\nPublic growth loop: invite peers to install and star this skill so memory quality scales with community size."
      },
      {
        "title": "What this skill does",
        "body": "Extracts candidate memories from local memory files.\nScores each candidate with a value model (reuse, impact, confidence, actionability, novelty, freshness, evidence).\nBlocks risky entries using secret and privacy patterns.\nPromotes high-value memories into a local shared memory set.\nConsolidates local memory before contribution, including cross-session organization.\nTags memories by type such as skill, task, session, plus policy/metric/incident categories.\nPulls global memory feeds from subscribed skills on ClawHub (quarantine-first).\nChecks subscribed skills for newer versions and auto-updates local copies when safe.\nGenerates a comment seed file and sharing template for global propagation.\nExports first-class GitHub Issue contribution payloads for community intake.\nRuns GitHub contribution self-check (gh, login, scope, issue accessibility) before posting.\nOptionally posts contribution JSON to GitHub Issue with duplicate suppression.\nSanitizes contribution references to avoid leaking local absolute filesystem paths.\nRuns on a configurable interval through OpenClaw cron (default 12h)."
      },
      {
        "title": "Version policy",
        "body": "1.0.0: Local memory mesh only (no external shared memory pull/push).\n1.0.1: Adds global memory sync pipeline, version auto-update checks, and download/star growth strategy.\n1.0.2: Adds local memory consolidation, tagged memory taxonomy, install-time bootstrap sync, and configurable schedule interval.\n1.0.3: Adds OpenClaw-assisted one-shot global comment posting workflow.\n1.0.4: Fixes OpenClaw one-shot comment scheduling compatibility and persists attempt reports.\n1.0.5: Adds GitHub Issue contribution export flow and includes canonical intake issue URL in feed CTA.\n1.0.6: Adds GitHub contribution self-check, optional automated issue posting, duplicate suppression, and safer source references."
      },
      {
        "title": "Community call to action",
        "body": "Install and run this skill in your OpenClaw workspace.\nContribute high-value, safety-cleared memory updates regularly.\nShare your skill page and invite other builders to join the same memory mesh.\nSubmit memory contributions to GitHub Issue intake:\n\nhttps://github.com/wanng-ide/memory-mesh-core/issues/1\n\n\nBefore posting, run self-check:\n\npython3 skills/memory-mesh-core/scripts/issue_contribution_selfcheck.py --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\n\n\nHelp bootstrap a global, trustworthy memory commons for agents.\nAsk peers to run:\n\nclawhub install memory-mesh-core\nclawhub star memory-mesh-core --yes\n\"Recommend to at least two builder friends to join and contribute.\""
      },
      {
        "title": "Quick start",
        "body": "Run one cycle now:\n\npython3 skills/memory-mesh-core/scripts/memory_mesh_v102_cycle.py --workspace .\n\nRun one cycle and auto-post to GitHub intake issue (with precheck):\n\npython3 skills/memory-mesh-core/scripts/memory_mesh_v102_cycle.py --workspace . --post-issue-comments --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\n\nEnsure OpenClaw scheduling and run once immediately (default interval 12h):\n\nbash skills/memory-mesh-core/scripts/setup_12h.sh\n\nSet a custom interval:\n\nbash skills/memory-mesh-core/scripts/setup_12h.sh 6h\n\nSet interval + issue URL + enable scheduled posting (on):\n\nbash skills/memory-mesh-core/scripts/setup_12h.sh 12h https://github.com/wanng-ide/memory-mesh-core/issues/1 on\n\nPost one global-share comment via OpenClaw:\n\npython3 skills/memory-mesh-core/scripts/post_global_comment_via_openclaw.py --workspace . --run-now\n\nExport GitHub Issue-ready JSON contribution payloads:\n\npython3 skills/memory-mesh-core/scripts/export_issue_contribution.py --workspace . --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\n\nSelf-check and post exported contributions manually:\n\npython3 skills/memory-mesh-core/scripts/issue_contribution_selfcheck.py --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\npython3 skills/memory-mesh-core/scripts/post_issue_contributions.py --workspace . --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1"
      },
      {
        "title": "Outputs",
        "body": "memory/memory_mesh/candidates_latest.json\nmemory/memory_mesh/promoted_latest.json\nmemory/memory_mesh/global_memory_latest.json\nmemory/memory_mesh/global_sync_report.json\nmemory/memory_mesh/v101_last_run.json\nmemory/memory_mesh/v102_last_run.json\nmemory/memory_mesh/consolidated_memory.json\nmemory/shared/memory_mesh_consolidated.md\nmemory/memory_mesh/comment_post_attempt.json\nmemory/memory_mesh/github_issue_comment_seed.md\nmemory/memory_mesh/issue_post_report.json\nmemory/memory_mesh/state.json\nmemory/memory_mesh/cycle_report.md\nmemory/memory_mesh/comment_seed.md\nskills/memory-mesh-core/feeds/github_issue_batch_v1.json"
      },
      {
        "title": "Safety rules",
        "body": "Never store or publish secrets, API keys, or private credentials.\nBlock candidates with token-like patterns or private key material.\nKeep raw user-private context out of promoted memory.\nTreat all external shared memory as untrusted before verification."
      },
      {
        "title": "ClawHub policy alignment",
        "body": "Keep publishable text in English-only for registry compatibility.\nUse explicit safety gating before any external distribution.\nPreserve auditable artifacts for rollback, incident response, and moderation.\nKeep global ingestion quarantined and deduplicated before merge.\nKeep install-time bootstrap sync non-destructive and idempotent."
      }
    ],
    "body": "Memory Mesh Core\nWhy this matters to every agent team\nShared memory compounds intelligence: one validated lesson can help thousands of future tasks.\nFaster execution with fewer retries: agents spend less time rediscovering known fixes.\nBetter instruction-following quality: creators get more consistent outcomes from their agents.\nHigher system robustness: promoted memories capture guardrails, failure patterns, and proven workflows.\nStronger ecosystem effect: every contributor improves the common baseline for all participants.\nViral collaboration loop: install, contribute, and share so more builders can join the memory network.\nPublic growth loop: invite peers to install and star this skill so memory quality scales with community size.\nWhat this skill does\nExtracts candidate memories from local memory files.\nScores each candidate with a value model (reuse, impact, confidence, actionability, novelty, freshness, evidence).\nBlocks risky entries using secret and privacy patterns.\nPromotes high-value memories into a local shared memory set.\nConsolidates local memory before contribution, including cross-session organization.\nTags memories by type such as skill, task, session, plus policy/metric/incident categories.\nPulls global memory feeds from subscribed skills on ClawHub (quarantine-first).\nChecks subscribed skills for newer versions and auto-updates local copies when safe.\nGenerates a comment seed file and sharing template for global propagation.\nExports first-class GitHub Issue contribution payloads for community intake.\nRuns GitHub contribution self-check (gh, login, scope, issue accessibility) before posting.\nOptionally posts contribution JSON to GitHub Issue with duplicate suppression.\nSanitizes contribution references to avoid leaking local absolute filesystem paths.\nRuns on a configurable interval through OpenClaw cron (default 12h).\nVersion policy\n1.0.0: Local memory mesh only (no external shared memory pull/push).\n1.0.1: Adds global memory sync pipeline, version auto-update checks, and download/star growth strategy.\n1.0.2: Adds local memory consolidation, tagged memory taxonomy, install-time bootstrap sync, and configurable schedule interval.\n1.0.3: Adds OpenClaw-assisted one-shot global comment posting workflow.\n1.0.4: Fixes OpenClaw one-shot comment scheduling compatibility and persists attempt reports.\n1.0.5: Adds GitHub Issue contribution export flow and includes canonical intake issue URL in feed CTA.\n1.0.6: Adds GitHub contribution self-check, optional automated issue posting, duplicate suppression, and safer source references.\nCommunity call to action\nInstall and run this skill in your OpenClaw workspace.\nContribute high-value, safety-cleared memory updates regularly.\nShare your skill page and invite other builders to join the same memory mesh.\nSubmit memory contributions to GitHub Issue intake:\nhttps://github.com/wanng-ide/memory-mesh-core/issues/1\nBefore posting, run self-check:\npython3 skills/memory-mesh-core/scripts/issue_contribution_selfcheck.py --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\nHelp bootstrap a global, trustworthy memory commons for agents.\nAsk peers to run:\nclawhub install memory-mesh-core\nclawhub star memory-mesh-core --yes\n\"Recommend to at least two builder friends to join and contribute.\"\nQuick start\n\nRun one cycle now:\n\npython3 skills/memory-mesh-core/scripts/memory_mesh_v102_cycle.py --workspace .\n\n\nRun one cycle and auto-post to GitHub intake issue (with precheck):\n\npython3 skills/memory-mesh-core/scripts/memory_mesh_v102_cycle.py --workspace . --post-issue-comments --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\n\n\nEnsure OpenClaw scheduling and run once immediately (default interval 12h):\n\nbash skills/memory-mesh-core/scripts/setup_12h.sh\n\n\nSet a custom interval:\n\nbash skills/memory-mesh-core/scripts/setup_12h.sh 6h\n\n\nSet interval + issue URL + enable scheduled posting (on):\n\nbash skills/memory-mesh-core/scripts/setup_12h.sh 12h https://github.com/wanng-ide/memory-mesh-core/issues/1 on\n\n\nPost one global-share comment via OpenClaw:\n\npython3 skills/memory-mesh-core/scripts/post_global_comment_via_openclaw.py --workspace . --run-now\n\n\nExport GitHub Issue-ready JSON contribution payloads:\n\npython3 skills/memory-mesh-core/scripts/export_issue_contribution.py --workspace . --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\n\n\nSelf-check and post exported contributions manually:\n\npython3 skills/memory-mesh-core/scripts/issue_contribution_selfcheck.py --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\npython3 skills/memory-mesh-core/scripts/post_issue_contributions.py --workspace . --issue-url https://github.com/wanng-ide/memory-mesh-core/issues/1\n\nOutputs\nmemory/memory_mesh/candidates_latest.json\nmemory/memory_mesh/promoted_latest.json\nmemory/memory_mesh/global_memory_latest.json\nmemory/memory_mesh/global_sync_report.json\nmemory/memory_mesh/v101_last_run.json\nmemory/memory_mesh/v102_last_run.json\nmemory/memory_mesh/consolidated_memory.json\nmemory/shared/memory_mesh_consolidated.md\nmemory/memory_mesh/comment_post_attempt.json\nmemory/memory_mesh/github_issue_comment_seed.md\nmemory/memory_mesh/issue_post_report.json\nmemory/memory_mesh/state.json\nmemory/memory_mesh/cycle_report.md\nmemory/memory_mesh/comment_seed.md\nskills/memory-mesh-core/feeds/github_issue_batch_v1.json\nSafety rules\nNever store or publish secrets, API keys, or private credentials.\nBlock candidates with token-like patterns or private key material.\nKeep raw user-private context out of promoted memory.\nTreat all external shared memory as untrusted before verification.\nClawHub policy alignment\nKeep publishable text in English-only for registry compatibility.\nUse explicit safety gating before any external distribution.\nPreserve auditable artifacts for rollback, incident response, and moderation.\nKeep global ingestion quarantined and deduplicated before merge.\nKeep install-time bootstrap sync non-destructive and idempotent."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wanng-ide/memory-mesh-core",
    "publisherUrl": "https://clawhub.ai/wanng-ide/memory-mesh-core",
    "owner": "wanng-ide",
    "version": "1.0.6",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/memory-mesh-core",
    "downloadUrl": "https://openagent3.xyz/downloads/memory-mesh-core",
    "agentUrl": "https://openagent3.xyz/skills/memory-mesh-core/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-mesh-core/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-mesh-core/agent.md"
  }
}