{
  "schemaVersion": "1.0",
  "item": {
    "slug": "aisa-multi-source-search",
    "name": "AIsa Multi Source Search",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/AIsaPay/aisa-multi-source-search",
    "canonicalUrl": "https://clawhub.ai/AIsaPay/aisa-multi-source-search",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/aisa-multi-source-search",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=aisa-multi-source-search",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/search_client.py"
    ],
    "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/aisa-multi-source-search"
    },
    "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/aisa-multi-source-search",
    "agentPageUrl": "https://openagent3.xyz/skills/aisa-multi-source-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/aisa-multi-source-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/aisa-multi-source-search/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": "OpenClaw Search 🔍",
        "body": "Intelligent search for autonomous agents. Powered by AIsa.\n\nOne API key. Multi-source retrieval. Confidence-scored answers.\n\nInspired by AIsa Verity - A next-generation search agent with trust-scored answers."
      },
      {
        "title": "Research Assistant",
        "body": "\"Search for the latest papers on transformer architectures from 2024-2025\""
      },
      {
        "title": "Market Research",
        "body": "\"Find all web articles about AI startup funding in Q4 2025\""
      },
      {
        "title": "Competitive Analysis",
        "body": "\"Search for reviews and comparisons of RAG frameworks\""
      },
      {
        "title": "News Aggregation",
        "body": "\"Get the latest news about quantum computing breakthroughs\""
      },
      {
        "title": "Deep Dive Research",
        "body": "\"Smart search combining web and academic sources on 'autonomous agents'\""
      },
      {
        "title": "Quick Start",
        "body": "export AISA_API_KEY=\"your-key\""
      },
      {
        "title": "🏗️ Architecture: Multi-Stage Orchestration",
        "body": "OpenClaw Search employs a Two-Phase Retrieval Strategy for comprehensive results:"
      },
      {
        "title": "Phase 1: Discovery (Parallel Retrieval)",
        "body": "Query 4 distinct search streams simultaneously:\n\nScholar: Deep academic retrieval\nWeb: Structured web search\nSmart: Intelligent mixed-mode search\nTavily: External validation signal"
      },
      {
        "title": "Phase 2: Reasoning (Meta-Analysis)",
        "body": "Use AIsa Explain to perform meta-analysis on search results, generating:\n\nConfidence scores (0-100)\nSource agreement analysis\nSynthesized answers\n\n┌─────────────────────────────────────────────────────────────┐\n│                      User Query                              │\n└─────────────────────────────────────────────────────────────┘\n                              │\n              ┌───────────────┼───────────────┐\n              ▼               ▼               ▼\n        ┌─────────┐     ┌─────────┐     ┌─────────┐\n        │ Scholar │     │   Web   │     │  Smart  │\n        └─────────┘     └─────────┘     └─────────┘\n              │               │               │\n              └───────────────┼───────────────┘\n                              ▼\n                    ┌─────────────────┐\n                    │  AIsa Explain   │\n                    │ (Meta-Analysis) │\n                    └─────────────────┘\n                              │\n                              ▼\n                    ┌─────────────────┐\n                    │ Confidence Score│\n                    │  + Synthesis    │\n                    └─────────────────┘"
      },
      {
        "title": "Web Search",
        "body": "# Basic web search\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/web?query=AI+frameworks&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\"\n\n# Full text search (with page content)\ncurl -X POST \"https://api.aisa.one/apis/v1/search/full?query=latest+AI+news&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\""
      },
      {
        "title": "Academic/Scholar Search",
        "body": "# Search academic papers\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/scholar?query=transformer+models&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\"\n\n# With year filter\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/scholar?query=LLM&max_num_results=10&as_ylo=2024&as_yhi=2025\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\""
      },
      {
        "title": "Smart Search (Web + Academic Combined)",
        "body": "# Intelligent hybrid search\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/smart?query=machine+learning+optimization&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\""
      },
      {
        "title": "Tavily Integration (Advanced)",
        "body": "# Tavily search\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/search\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"query\":\"latest AI developments\"}'\n\n# Extract content from URLs\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/extract\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"urls\":[\"https://example.com/article\"]}'\n\n# Crawl web pages\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/crawl\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"url\":\"https://example.com\",\"max_depth\":2}'\n\n# Site map\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/map\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"url\":\"https://example.com\"}'"
      },
      {
        "title": "Explain Search Results (Meta-Analysis)",
        "body": "# Generate explanations with confidence scoring\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/explain\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"results\":[...],\"language\":\"en\",\"format\":\"summary\"}'"
      },
      {
        "title": "📊 Confidence Scoring Engine",
        "body": "Unlike standard RAG systems, OpenClaw Search evaluates credibility and consensus:"
      },
      {
        "title": "Scoring Rubric",
        "body": "FactorWeightDescriptionSource Quality40%Academic > Smart/Web > ExternalAgreement Analysis35%Cross-source consensus checkingRecency15%Newer sources weighted higherRelevance10%Query-result semantic match"
      },
      {
        "title": "Score Interpretation",
        "body": "ScoreConfidence LevelMeaning90-100Very HighStrong consensus across academic and web sources70-89HighGood agreement, reliable sources50-69MediumMixed signals, verify independently30-49LowConflicting sources, use caution0-29Very LowInsufficient or contradictory data"
      },
      {
        "title": "Python Client",
        "body": "# Web search\npython3 {baseDir}/scripts/search_client.py web --query \"latest AI news\" --count 10\n\n# Academic search\npython3 {baseDir}/scripts/search_client.py scholar --query \"transformer architecture\" --count 10\npython3 {baseDir}/scripts/search_client.py scholar --query \"LLM\" --year-from 2024 --year-to 2025\n\n# Smart search (web + academic)\npython3 {baseDir}/scripts/search_client.py smart --query \"autonomous agents\" --count 10\n\n# Full text search\npython3 {baseDir}/scripts/search_client.py full --query \"AI startup funding\"\n\n# Tavily operations\npython3 {baseDir}/scripts/search_client.py tavily-search --query \"AI developments\"\npython3 {baseDir}/scripts/search_client.py tavily-extract --urls \"https://example.com/article\"\n\n# Multi-source search with confidence scoring\npython3 {baseDir}/scripts/search_client.py verity --query \"Is quantum computing ready for enterprise?\""
      },
      {
        "title": "API Endpoints Reference",
        "body": "EndpointMethodDescription/scholar/search/webPOSTWeb search with structured results/scholar/search/scholarPOSTAcademic paper search/scholar/search/smartPOSTIntelligent hybrid search/scholar/explainPOSTGenerate result explanations/search/fullPOSTFull text search with content/search/smartPOSTSmart web search/tavily/searchPOSTTavily search integration/tavily/extractPOSTExtract content from URLs/tavily/crawlPOSTCrawl web pages/tavily/mapPOSTGenerate site maps"
      },
      {
        "title": "Search Parameters",
        "body": "ParameterTypeDescriptionquerystringSearch query (required)max_num_resultsintegerMax results (1-100, default 10)as_ylointegerYear lower bound (scholar only)as_yhiintegerYear upper bound (scholar only)"
      },
      {
        "title": "🚀 Building a Verity-Style Agent",
        "body": "Want to build your own confidence-scored search agent? Here's the pattern:"
      },
      {
        "title": "1. Parallel Discovery",
        "body": "import asyncio\n\nasync def discover(query):\n    \"\"\"Phase 1: Parallel retrieval from multiple sources.\"\"\"\n    tasks = [\n        search_scholar(query),\n        search_web(query),\n        search_smart(query),\n        search_tavily(query)\n    ]\n    results = await asyncio.gather(*tasks)\n    return {\n        \"scholar\": results[0],\n        \"web\": results[1],\n        \"smart\": results[2],\n        \"tavily\": results[3]\n    }"
      },
      {
        "title": "2. Confidence Scoring",
        "body": "def score_confidence(results):\n    \"\"\"Calculate deterministic confidence score.\"\"\"\n    score = 0\n    \n    # Source quality (40%)\n    if results[\"scholar\"]:\n        score += 40 * len(results[\"scholar\"]) / 10\n    \n    # Agreement analysis (35%)\n    claims = extract_claims(results)\n    agreement = analyze_agreement(claims)\n    score += 35 * agreement\n    \n    # Recency (15%)\n    recency = calculate_recency(results)\n    score += 15 * recency\n    \n    # Relevance (10%)\n    relevance = calculate_relevance(results, query)\n    score += 10 * relevance\n    \n    return min(100, score)"
      },
      {
        "title": "3. Synthesis",
        "body": "async def synthesize(query, results, score):\n    \"\"\"Generate final answer with citations.\"\"\"\n    explanation = await explain_results(results)\n    return {\n        \"answer\": explanation[\"summary\"],\n        \"confidence\": score,\n        \"sources\": explanation[\"citations\"],\n        \"claims\": explanation[\"claims\"]\n    }\n\nFor a complete implementation, see AIsa Verity."
      },
      {
        "title": "Pricing",
        "body": "APICostWeb search~$0.001Scholar search~$0.002Smart search~$0.002Tavily search~$0.002Explain~$0.003\n\nEvery response includes usage.cost and usage.credits_remaining."
      },
      {
        "title": "Get Started",
        "body": "Sign up at aisa.one\nGet your API key\nAdd credits (pay-as-you-go)\nSet environment variable: export AISA_API_KEY=\"your-key\""
      },
      {
        "title": "Full API Reference",
        "body": "See API Reference for complete endpoint documentation."
      },
      {
        "title": "Resources",
        "body": "AIsa Verity - Reference implementation of confidence-scored search agent\nAIsa Documentation - Complete API documentation"
      }
    ],
    "body": "OpenClaw Search 🔍\n\nIntelligent search for autonomous agents. Powered by AIsa.\n\nOne API key. Multi-source retrieval. Confidence-scored answers.\n\nInspired by AIsa Verity - A next-generation search agent with trust-scored answers.\n\n🔥 What Can You Do?\nResearch Assistant\n\"Search for the latest papers on transformer architectures from 2024-2025\"\n\nMarket Research\n\"Find all web articles about AI startup funding in Q4 2025\"\n\nCompetitive Analysis\n\"Search for reviews and comparisons of RAG frameworks\"\n\nNews Aggregation\n\"Get the latest news about quantum computing breakthroughs\"\n\nDeep Dive Research\n\"Smart search combining web and academic sources on 'autonomous agents'\"\n\nQuick Start\nexport AISA_API_KEY=\"your-key\"\n\n🏗️ Architecture: Multi-Stage Orchestration\n\nOpenClaw Search employs a Two-Phase Retrieval Strategy for comprehensive results:\n\nPhase 1: Discovery (Parallel Retrieval)\n\nQuery 4 distinct search streams simultaneously:\n\nScholar: Deep academic retrieval\nWeb: Structured web search\nSmart: Intelligent mixed-mode search\nTavily: External validation signal\nPhase 2: Reasoning (Meta-Analysis)\n\nUse AIsa Explain to perform meta-analysis on search results, generating:\n\nConfidence scores (0-100)\nSource agreement analysis\nSynthesized answers\n┌─────────────────────────────────────────────────────────────┐\n│                      User Query                              │\n└─────────────────────────────────────────────────────────────┘\n                              │\n              ┌───────────────┼───────────────┐\n              ▼               ▼               ▼\n        ┌─────────┐     ┌─────────┐     ┌─────────┐\n        │ Scholar │     │   Web   │     │  Smart  │\n        └─────────┘     └─────────┘     └─────────┘\n              │               │               │\n              └───────────────┼───────────────┘\n                              ▼\n                    ┌─────────────────┐\n                    │  AIsa Explain   │\n                    │ (Meta-Analysis) │\n                    └─────────────────┘\n                              │\n                              ▼\n                    ┌─────────────────┐\n                    │ Confidence Score│\n                    │  + Synthesis    │\n                    └─────────────────┘\n\nCore Capabilities\nWeb Search\n# Basic web search\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/web?query=AI+frameworks&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\"\n\n# Full text search (with page content)\ncurl -X POST \"https://api.aisa.one/apis/v1/search/full?query=latest+AI+news&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\"\n\nAcademic/Scholar Search\n# Search academic papers\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/scholar?query=transformer+models&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\"\n\n# With year filter\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/scholar?query=LLM&max_num_results=10&as_ylo=2024&as_yhi=2025\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\"\n\nSmart Search (Web + Academic Combined)\n# Intelligent hybrid search\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/search/smart?query=machine+learning+optimization&max_num_results=10\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\"\n\nTavily Integration (Advanced)\n# Tavily search\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/search\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"query\":\"latest AI developments\"}'\n\n# Extract content from URLs\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/extract\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"urls\":[\"https://example.com/article\"]}'\n\n# Crawl web pages\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/crawl\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"url\":\"https://example.com\",\"max_depth\":2}'\n\n# Site map\ncurl -X POST \"https://api.aisa.one/apis/v1/tavily/map\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"url\":\"https://example.com\"}'\n\nExplain Search Results (Meta-Analysis)\n# Generate explanations with confidence scoring\ncurl -X POST \"https://api.aisa.one/apis/v1/scholar/explain\" \\\n  -H \"Authorization: Bearer $AISA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"results\":[...],\"language\":\"en\",\"format\":\"summary\"}'\n\n📊 Confidence Scoring Engine\n\nUnlike standard RAG systems, OpenClaw Search evaluates credibility and consensus:\n\nScoring Rubric\nFactor\tWeight\tDescription\nSource Quality\t40%\tAcademic > Smart/Web > External\nAgreement Analysis\t35%\tCross-source consensus checking\nRecency\t15%\tNewer sources weighted higher\nRelevance\t10%\tQuery-result semantic match\nScore Interpretation\nScore\tConfidence Level\tMeaning\n90-100\tVery High\tStrong consensus across academic and web sources\n70-89\tHigh\tGood agreement, reliable sources\n50-69\tMedium\tMixed signals, verify independently\n30-49\tLow\tConflicting sources, use caution\n0-29\tVery Low\tInsufficient or contradictory data\nPython Client\n# Web search\npython3 {baseDir}/scripts/search_client.py web --query \"latest AI news\" --count 10\n\n# Academic search\npython3 {baseDir}/scripts/search_client.py scholar --query \"transformer architecture\" --count 10\npython3 {baseDir}/scripts/search_client.py scholar --query \"LLM\" --year-from 2024 --year-to 2025\n\n# Smart search (web + academic)\npython3 {baseDir}/scripts/search_client.py smart --query \"autonomous agents\" --count 10\n\n# Full text search\npython3 {baseDir}/scripts/search_client.py full --query \"AI startup funding\"\n\n# Tavily operations\npython3 {baseDir}/scripts/search_client.py tavily-search --query \"AI developments\"\npython3 {baseDir}/scripts/search_client.py tavily-extract --urls \"https://example.com/article\"\n\n# Multi-source search with confidence scoring\npython3 {baseDir}/scripts/search_client.py verity --query \"Is quantum computing ready for enterprise?\"\n\nAPI Endpoints Reference\nEndpoint\tMethod\tDescription\n/scholar/search/web\tPOST\tWeb search with structured results\n/scholar/search/scholar\tPOST\tAcademic paper search\n/scholar/search/smart\tPOST\tIntelligent hybrid search\n/scholar/explain\tPOST\tGenerate result explanations\n/search/full\tPOST\tFull text search with content\n/search/smart\tPOST\tSmart web search\n/tavily/search\tPOST\tTavily search integration\n/tavily/extract\tPOST\tExtract content from URLs\n/tavily/crawl\tPOST\tCrawl web pages\n/tavily/map\tPOST\tGenerate site maps\nSearch Parameters\nParameter\tType\tDescription\nquery\tstring\tSearch query (required)\nmax_num_results\tinteger\tMax results (1-100, default 10)\nas_ylo\tinteger\tYear lower bound (scholar only)\nas_yhi\tinteger\tYear upper bound (scholar only)\n🚀 Building a Verity-Style Agent\n\nWant to build your own confidence-scored search agent? Here's the pattern:\n\n1. Parallel Discovery\nimport asyncio\n\nasync def discover(query):\n    \"\"\"Phase 1: Parallel retrieval from multiple sources.\"\"\"\n    tasks = [\n        search_scholar(query),\n        search_web(query),\n        search_smart(query),\n        search_tavily(query)\n    ]\n    results = await asyncio.gather(*tasks)\n    return {\n        \"scholar\": results[0],\n        \"web\": results[1],\n        \"smart\": results[2],\n        \"tavily\": results[3]\n    }\n\n2. Confidence Scoring\ndef score_confidence(results):\n    \"\"\"Calculate deterministic confidence score.\"\"\"\n    score = 0\n    \n    # Source quality (40%)\n    if results[\"scholar\"]:\n        score += 40 * len(results[\"scholar\"]) / 10\n    \n    # Agreement analysis (35%)\n    claims = extract_claims(results)\n    agreement = analyze_agreement(claims)\n    score += 35 * agreement\n    \n    # Recency (15%)\n    recency = calculate_recency(results)\n    score += 15 * recency\n    \n    # Relevance (10%)\n    relevance = calculate_relevance(results, query)\n    score += 10 * relevance\n    \n    return min(100, score)\n\n3. Synthesis\nasync def synthesize(query, results, score):\n    \"\"\"Generate final answer with citations.\"\"\"\n    explanation = await explain_results(results)\n    return {\n        \"answer\": explanation[\"summary\"],\n        \"confidence\": score,\n        \"sources\": explanation[\"citations\"],\n        \"claims\": explanation[\"claims\"]\n    }\n\n\nFor a complete implementation, see AIsa Verity.\n\nPricing\nAPI\tCost\nWeb search\t~$0.001\nScholar search\t~$0.002\nSmart search\t~$0.002\nTavily search\t~$0.002\nExplain\t~$0.003\n\nEvery response includes usage.cost and usage.credits_remaining.\n\nGet Started\nSign up at aisa.one\nGet your API key\nAdd credits (pay-as-you-go)\nSet environment variable: export AISA_API_KEY=\"your-key\"\nFull API Reference\n\nSee API Reference for complete endpoint documentation.\n\nResources\nAIsa Verity - Reference implementation of confidence-scored search agent\nAIsa Documentation - Complete API documentation"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AIsaPay/aisa-multi-source-search",
    "publisherUrl": "https://clawhub.ai/AIsaPay/aisa-multi-source-search",
    "owner": "AIsaPay",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/aisa-multi-source-search",
    "downloadUrl": "https://openagent3.xyz/downloads/aisa-multi-source-search",
    "agentUrl": "https://openagent3.xyz/skills/aisa-multi-source-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/aisa-multi-source-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/aisa-multi-source-search/agent.md"
  }
}