{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-bee",
    "name": "BEE Belief Extraction Engine",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/vashkartik/openclaw-bee",
    "canonicalUrl": "https://clawhub.ai/vashkartik/openclaw-bee",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-bee",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-bee",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/openclaw-bee"
    },
    "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/openclaw-bee",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-bee/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-bee/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-bee/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "BEE — Belief Extraction Engine",
        "body": "Give your OpenClaw agents persistent, structured memory across sessions."
      },
      {
        "title": "What BEE Does",
        "body": "BEE hooks into the OpenClaw lifecycle and:\n\nExtracts beliefs at session end via a lightweight LLM call (Haiku by default)\nInjects recalled context before every agent spawn\nScopes by namespace — each agent (VECTOR, FORGE, ORACLE, etc.) has isolated beliefs\nDeduplicates — cosine similarity check prevents duplicate beliefs (>0.92 → merge)\nTracks spawns — monitors subagent budget per session\n\nBeliefs live in a SQLite database (vector.db) and persist indefinitely across restarts."
      },
      {
        "title": "Step 1 — Install the package",
        "body": "From npm (recommended):\n\nnpm install -g @skysphere-labs/openclaw-bee\n\nFrom GitHub (latest):\n\nnpm install -g github:skysphere-labs/openclaw-bee"
      },
      {
        "title": "Step 2 — Configure openclaw.json",
        "body": "Add BEE to your extensions in ~/.openclaw/openclaw.json:\n\n{\n  \"extensions\": {\n    \"entries\": {\n      \"bee\": {\n        \"enabled\": true,\n        \"config\": {\n          \"dbPath\": \"~/.openclaw/workspace/state/vector.db\",\n          \"agentId\": \"main\",\n          \"extractionEnabled\": true,\n          \"extractionModel\": \"anthropic/claude-haiku-4-5\",\n          \"maxCoreBeliefs\": 10,\n          \"maxActiveBeliefs\": 5,\n          \"maxRecalledBeliefs\": 5\n        }\n      }\n    }\n  }\n}"
      },
      {
        "title": "Step 3 — Restart the gateway",
        "body": "openclaw gateway restart\n\nBEE will run its database migration on first start and begin capturing beliefs."
      },
      {
        "title": "Configuration Options",
        "body": "OptionDefaultDescriptiondbPathrequiredPath to your SQLite databaseagentId\"main\"Namespace for belief scopingextractionEnabledtrueEnable/disable belief extractionextractionModel\"anthropic/claude-haiku-4-5\"Model used for extraction (cheapest works well)extractionMinConfidence0.55Minimum confidence to store a belief (0-1)maxCoreBeliefs10Core beliefs injected into every sessionmaxActiveBeliefs5Recently active beliefs injectedmaxRecalledBeliefs5Semantically recalled beliefs per querymaxOutputChars2000Max chars of belief context injecteddebugfalseEnable verbose loggingspawnBudgetWarning20Warn when subagent spawns exceed this threshold"
      },
      {
        "title": "Verifying It Works",
        "body": "After restart, ask your agent:\n\n\"How many beliefs do you have?\"\n\nOr check directly:\n\nsqlite3 ~/.openclaw/workspace/state/vector.db \"SELECT COUNT(*) FROM beliefs\"\n\nYou should see beliefs accumulate after sessions complete."
      },
      {
        "title": "Multi-Agent Setup",
        "body": "For setups with multiple named agents (VECTOR, FORGE, ORACLE, etc.), use different agentId values per agent spawn. BEE scopes beliefs by agentId so each PM has isolated memory."
      },
      {
        "title": "Source",
        "body": "GitHub: https://github.com/skysphere-labs/openclaw-bee\nnpm: https://www.npmjs.com/package/@skysphere-labs/openclaw-bee\nBuilt by Skysphere AI Labs"
      }
    ],
    "body": "BEE — Belief Extraction Engine\n\nGive your OpenClaw agents persistent, structured memory across sessions.\n\nWhat BEE Does\n\nBEE hooks into the OpenClaw lifecycle and:\n\nExtracts beliefs at session end via a lightweight LLM call (Haiku by default)\nInjects recalled context before every agent spawn\nScopes by namespace — each agent (VECTOR, FORGE, ORACLE, etc.) has isolated beliefs\nDeduplicates — cosine similarity check prevents duplicate beliefs (>0.92 → merge)\nTracks spawns — monitors subagent budget per session\n\nBeliefs live in a SQLite database (vector.db) and persist indefinitely across restarts.\n\nInstallation\nStep 1 — Install the package\n\nFrom npm (recommended):\n\nnpm install -g @skysphere-labs/openclaw-bee\n\n\nFrom GitHub (latest):\n\nnpm install -g github:skysphere-labs/openclaw-bee\n\nStep 2 — Configure openclaw.json\n\nAdd BEE to your extensions in ~/.openclaw/openclaw.json:\n\n{\n  \"extensions\": {\n    \"entries\": {\n      \"bee\": {\n        \"enabled\": true,\n        \"config\": {\n          \"dbPath\": \"~/.openclaw/workspace/state/vector.db\",\n          \"agentId\": \"main\",\n          \"extractionEnabled\": true,\n          \"extractionModel\": \"anthropic/claude-haiku-4-5\",\n          \"maxCoreBeliefs\": 10,\n          \"maxActiveBeliefs\": 5,\n          \"maxRecalledBeliefs\": 5\n        }\n      }\n    }\n  }\n}\n\nStep 3 — Restart the gateway\nopenclaw gateway restart\n\n\nBEE will run its database migration on first start and begin capturing beliefs.\n\nConfiguration Options\nOption\tDefault\tDescription\ndbPath\trequired\tPath to your SQLite database\nagentId\t\"main\"\tNamespace for belief scoping\nextractionEnabled\ttrue\tEnable/disable belief extraction\nextractionModel\t\"anthropic/claude-haiku-4-5\"\tModel used for extraction (cheapest works well)\nextractionMinConfidence\t0.55\tMinimum confidence to store a belief (0-1)\nmaxCoreBeliefs\t10\tCore beliefs injected into every session\nmaxActiveBeliefs\t5\tRecently active beliefs injected\nmaxRecalledBeliefs\t5\tSemantically recalled beliefs per query\nmaxOutputChars\t2000\tMax chars of belief context injected\ndebug\tfalse\tEnable verbose logging\nspawnBudgetWarning\t20\tWarn when subagent spawns exceed this threshold\nVerifying It Works\n\nAfter restart, ask your agent:\n\n\"How many beliefs do you have?\"\n\nOr check directly:\n\nsqlite3 ~/.openclaw/workspace/state/vector.db \"SELECT COUNT(*) FROM beliefs\"\n\n\nYou should see beliefs accumulate after sessions complete.\n\nMulti-Agent Setup\n\nFor setups with multiple named agents (VECTOR, FORGE, ORACLE, etc.), use different agentId values per agent spawn. BEE scopes beliefs by agentId so each PM has isolated memory.\n\nSource\nGitHub: https://github.com/skysphere-labs/openclaw-bee\nnpm: https://www.npmjs.com/package/@skysphere-labs/openclaw-bee\nBuilt by Skysphere AI Labs"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/vashkartik/openclaw-bee",
    "publisherUrl": "https://clawhub.ai/vashkartik/openclaw-bee",
    "owner": "vashkartik",
    "version": "0.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-bee",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-bee",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-bee/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-bee/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-bee/agent.md"
  }
}