{
  "schemaVersion": "1.0",
  "item": {
    "slug": "percept-ambient",
    "name": "Percept Ambient",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/jarvis563/percept-ambient",
    "canonicalUrl": "https://clawhub.ai/jarvis563/percept-ambient",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/percept-ambient",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=percept-ambient",
    "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": "2026-04-30T16:55:25.780Z",
      "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/percept-ambient"
    },
    "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/percept-ambient",
    "agentPageUrl": "https://openagent3.xyz/skills/percept-ambient/agent",
    "manifestUrl": "https://openagent3.xyz/skills/percept-ambient/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/percept-ambient/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": "percept-ambient",
        "body": "Ambient intelligence mode — continuous context awareness without explicit commands."
      },
      {
        "title": "What it does",
        "body": "Runs in the background, building a knowledge graph of conversations, entities, and relationships over time. Your agent passively learns context from ambient speech — who you talk to, what projects are active, what decisions were made — without needing explicit commands."
      },
      {
        "title": "When to use",
        "body": "User wants always-on context awareness\nAgent needs background knowledge from daily conversations\nUser asks \"what do you know about [person/project]?\" based on overheard context"
      },
      {
        "title": "Requirements",
        "body": "percept-listen skill installed and running\npercept-summarize skill installed (for entity extraction)"
      },
      {
        "title": "How it works",
        "body": "All conversations are continuously captured and summarized\nEntities (people, companies, projects, topics) extracted automatically\nRelationships mapped between entities (works_on, client_of, mentioned_with)\nContext packets assembled on demand for any agent action\nFull-text search (FTS5) + vector search (LanceDB) for retrieval"
      },
      {
        "title": "Context packets",
        "body": "When your agent needs context, Percept assembles a Context Packet:\n\n{\n  \"recent_conversations\": [...],\n  \"resolved_entities\": [...],\n  \"relationships\": [...],\n  \"relevant_history\": [...]\n}\n\nThis gives the agent rich situational awareness without loading entire conversation histories."
      },
      {
        "title": "Vector search",
        "body": "Semantic search over utterances using NVIDIA NIM embeddings (primary) with all-MiniLM-L6-v2 as offline fallback. Stored in LanceDB (local, zero-infra).\n\n# Search via dashboard (port 8960) or API\ncurl localhost:8960/api/search?q=project+deadline&mode=hybrid"
      },
      {
        "title": "Privacy controls",
        "body": "All data stored locally in SQLite + LanceDB\nTTL auto-purge (configurable retention periods)\nNo audio stored — only transcripts\nDashboard → Settings → Privacy for granular controls"
      },
      {
        "title": "Real-time dashboard",
        "body": "Monitor ambient intelligence at http://localhost:8960:\n\nLive conversation feed\nEntity graph visualization\nSearch across all conversations\nAnalytics and usage stats"
      },
      {
        "title": "Links",
        "body": "GitHub: https://github.com/GetPercept/percept"
      }
    ],
    "body": "percept-ambient\n\nAmbient intelligence mode — continuous context awareness without explicit commands.\n\nWhat it does\n\nRuns in the background, building a knowledge graph of conversations, entities, and relationships over time. Your agent passively learns context from ambient speech — who you talk to, what projects are active, what decisions were made — without needing explicit commands.\n\nWhen to use\nUser wants always-on context awareness\nAgent needs background knowledge from daily conversations\nUser asks \"what do you know about [person/project]?\" based on overheard context\nRequirements\npercept-listen skill installed and running\npercept-summarize skill installed (for entity extraction)\nHow it works\nAll conversations are continuously captured and summarized\nEntities (people, companies, projects, topics) extracted automatically\nRelationships mapped between entities (works_on, client_of, mentioned_with)\nContext packets assembled on demand for any agent action\nFull-text search (FTS5) + vector search (LanceDB) for retrieval\nContext packets\n\nWhen your agent needs context, Percept assembles a Context Packet:\n\n{\n  \"recent_conversations\": [...],\n  \"resolved_entities\": [...],\n  \"relationships\": [...],\n  \"relevant_history\": [...]\n}\n\n\nThis gives the agent rich situational awareness without loading entire conversation histories.\n\nVector search\n\nSemantic search over utterances using NVIDIA NIM embeddings (primary) with all-MiniLM-L6-v2 as offline fallback. Stored in LanceDB (local, zero-infra).\n\n# Search via dashboard (port 8960) or API\ncurl localhost:8960/api/search?q=project+deadline&mode=hybrid\n\nPrivacy controls\nAll data stored locally in SQLite + LanceDB\nTTL auto-purge (configurable retention periods)\nNo audio stored — only transcripts\nDashboard → Settings → Privacy for granular controls\nReal-time dashboard\n\nMonitor ambient intelligence at http://localhost:8960:\n\nLive conversation feed\nEntity graph visualization\nSearch across all conversations\nAnalytics and usage stats\nLinks\nGitHub: https://github.com/GetPercept/percept"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jarvis563/percept-ambient",
    "publisherUrl": "https://clawhub.ai/jarvis563/percept-ambient",
    "owner": "jarvis563",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/percept-ambient",
    "downloadUrl": "https://openagent3.xyz/downloads/percept-ambient",
    "agentUrl": "https://openagent3.xyz/skills/percept-ambient/agent",
    "manifestUrl": "https://openagent3.xyz/skills/percept-ambient/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/percept-ambient/agent.md"
  }
}