{
  "schemaVersion": "1.0",
  "item": {
    "slug": "unsearch",
    "name": "UnSearch",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Rakesh1002/unsearch",
    "canonicalUrl": "https://clawhub.ai/Rakesh1002/unsearch",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/unsearch",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=unsearch",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "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. 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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/unsearch"
    },
    "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/unsearch",
    "agentPageUrl": "https://openagent3.xyz/skills/unsearch/agent",
    "manifestUrl": "https://openagent3.xyz/skills/unsearch/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/unsearch/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": "UnSearch Web Search Skill",
        "body": "Search the web, extract content, verify facts, and conduct deep research using the UnSearch API—an open-source Tavily/Exa alternative."
      },
      {
        "title": "Quick Start",
        "body": "Set your API key:\n\nexport UNSEARCH_API_KEY=\"uns_your_api_key\"\n\nGet a free API key at https://unsearch.dev (5,000 queries/month free)."
      },
      {
        "title": "API Endpoints",
        "body": "Base URL: https://api.unsearch.dev/api/v1\n\nAll requests require header: X-API-Key: $UNSEARCH_API_KEY"
      },
      {
        "title": "1. Web Search",
        "body": "Search the web with optional content scraping.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/search\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"query\": \"your search query\",\n    \"engines\": [\"google\", \"bing\", \"duckduckgo\"],\n    \"max_results\": 10,\n    \"scrape_content\": true\n  }'"
      },
      {
        "title": "Key Parameters",
        "body": "ParameterTypeDefaultDescriptionquerystringrequiredSearch query (1-500 chars)enginesstring[][\"google\",\"bing\",\"duckduckgo\"]Search enginesmax_resultsinteger10Results to return (1-100)scrape_contentbooleantrueExtract full page contentlanguagestring\"en\"ISO 639-1 language code"
      },
      {
        "title": "Response",
        "body": "{\n  \"results\": [\n    {\n      \"title\": \"Page Title\",\n      \"url\": \"https://example.com\",\n      \"snippet\": \"Search result snippet...\",\n      \"scraped_content\": {\n        \"text\": \"Full page content...\",\n        \"word_count\": 2500\n      }\n    }\n  ],\n  \"processing_time_ms\": 1500\n}"
      },
      {
        "title": "2. Agent Search (Tavily-Compatible)",
        "body": "AI-optimized search with optional answer generation.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/agent/search\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"query\": \"What is machine learning?\",\n    \"include_answer\": true,\n    \"max_results\": 5,\n    \"search_depth\": \"basic\"\n  }'"
      },
      {
        "title": "Key Parameters",
        "body": "ParameterTypeDefaultDescriptionquerystringrequiredSearch queryinclude_answerbool/stringfalseGenerate AI answer (true, \"basic\", \"advanced\", \"production\")search_depthstring\"basic\"basic, advanced, fastmax_resultsinteger5Results (1-20)include_raw_contentbooleanfalseInclude full page contentinclude_domainsstring[]nullOnly search these domainsexclude_domainsstring[]nullExclude these domains"
      },
      {
        "title": "Response",
        "body": "{\n  \"query\": \"What is machine learning?\",\n  \"answer\": \"Machine learning is a subset of AI...\",\n  \"results\": [\n    {\n      \"title\": \"Machine Learning - Wikipedia\",\n      \"url\": \"https://en.wikipedia.org/wiki/Machine_learning\",\n      \"content\": \"Machine learning is a branch of AI...\",\n      \"score\": 0.95\n    }\n  ],\n  \"response_time\": 1.25\n}"
      },
      {
        "title": "3. Content Extraction",
        "body": "Extract content from specific URLs.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/agent/extract\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"urls\": [\"https://example.com/article\"],\n    \"extract_depth\": \"basic\"\n  }'"
      },
      {
        "title": "Response",
        "body": "{\n  \"results\": [\n    {\n      \"url\": \"https://example.com/article\",\n      \"raw_content\": \"Full article text...\",\n      \"failed\": false\n    }\n  ]\n}"
      },
      {
        "title": "4. Deep Research",
        "body": "Multi-source research with AI synthesis.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/agent/research\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"query\": \"Impact of AI on healthcare\",\n    \"depth\": \"deep\",\n    \"max_sources\": 15,\n    \"include_analysis\": true\n  }'"
      },
      {
        "title": "Depth Levels",
        "body": "DepthSourcesUse Casequick3-5Fast overviewstandard5-10Balanced researchdeep10-20Thorough analysiscomprehensive20-30Expert-level"
      },
      {
        "title": "Response",
        "body": "{\n  \"executive_summary\": \"AI is transforming healthcare...\",\n  \"key_findings\": [\"AI diagnostics show 95% accuracy...\"],\n  \"sources\": [...],\n  \"model_used\": \"qwq-32b\"\n}"
      },
      {
        "title": "5. Fact Verification",
        "body": "Verify claims against multiple sources.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/verify/claim\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"claim\": \"GPT-4 was released in March 2023\",\n    \"depth\": \"thorough\"\n  }'"
      },
      {
        "title": "Response",
        "body": "{\n  \"verdict\": \"true\",\n  \"confidence\": 95,\n  \"summary\": \"GPT-4 was released March 14, 2023.\",\n  \"supporting_evidence\": [...],\n  \"sources_checked\": 12\n}\n\nVerdict values: true, false, partially_true, misleading, unverifiable"
      },
      {
        "title": "Python Examples",
        "body": "import httpx\nimport os\n\nAPI_KEY = os.environ[\"UNSEARCH_API_KEY\"]\nBASE_URL = \"https://api.unsearch.dev/api/v1\"\n\nasync def search(query: str, scrape: bool = False):\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            f\"{BASE_URL}/search\",\n            headers={\"X-API-Key\": API_KEY},\n            json={\n                \"query\": query,\n                \"max_results\": 10,\n                \"scrape_content\": scrape\n            }\n        )\n        return response.json()\n\nasync def agent_search(query: str, include_answer: bool = True):\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            f\"{BASE_URL}/agent/search\",\n            headers={\"X-API-Key\": API_KEY},\n            json={\n                \"query\": query,\n                \"include_answer\": include_answer,\n                \"max_results\": 5\n            }\n        )\n        return response.json()\n\nasync def extract_urls(urls: list[str]):\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            f\"{BASE_URL}/agent/extract\",\n            headers={\"X-API-Key\": API_KEY},\n            json={\"urls\": urls}\n        )\n        return response.json()"
      },
      {
        "title": "JavaScript Examples",
        "body": "const API_KEY = process.env.UNSEARCH_API_KEY;\nconst BASE_URL = \"https://api.unsearch.dev/api/v1\";\n\nasync function search(query, scrapeContent = false) {\n  const response = await fetch(`${BASE_URL}/search`, {\n    method: \"POST\",\n    headers: {\n      \"X-API-Key\": API_KEY,\n      \"Content-Type\": \"application/json\"\n    },\n    body: JSON.stringify({\n      query,\n      max_results: 10,\n      scrape_content: scrapeContent\n    })\n  });\n  return response.json();\n}\n\nasync function agentSearch(query, includeAnswer = true) {\n  const response = await fetch(`${BASE_URL}/agent/search`, {\n    method: \"POST\",\n    headers: {\n      \"X-API-Key\": API_KEY,\n      \"Content-Type\": \"application/json\"\n    },\n    body: JSON.stringify({\n      query,\n      include_answer: includeAnswer,\n      max_results: 5\n    })\n  });\n  return response.json();\n}"
      },
      {
        "title": "Rate Limits",
        "body": "PlanQueries/MonthRate LimitFree5,00010/minPro25,00060/minGrowth100,000200/minScale500,0001,000/min\n\nRate limit headers in response:\n\nX-RateLimit-Remaining: Requests left\nX-RateLimit-Reset: Reset timestamp"
      },
      {
        "title": "Privacy Mode",
        "body": "For sensitive queries, enable zero-retention:\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/search\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"X-Zero-Retention: true\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"query\": \"sensitive query\"}'"
      },
      {
        "title": "Error Handling",
        "body": "CodeDescription401Invalid API key429Rate limited (check Retry-After header)422Validation error500Server error"
      },
      {
        "title": "Additional Resources",
        "body": "Documentation: https://docs.unsearch.dev\nAPI Reference: https://docs.unsearch.dev/api\nSelf-hosting: https://github.com/unsearch-org/unsearch\nGet API Key: https://unsearch.dev"
      }
    ],
    "body": "UnSearch Web Search Skill\n\nSearch the web, extract content, verify facts, and conduct deep research using the UnSearch API—an open-source Tavily/Exa alternative.\n\nQuick Start\n\nSet your API key:\n\nexport UNSEARCH_API_KEY=\"uns_your_api_key\"\n\n\nGet a free API key at https://unsearch.dev (5,000 queries/month free).\n\nAPI Endpoints\n\nBase URL: https://api.unsearch.dev/api/v1\n\nAll requests require header: X-API-Key: $UNSEARCH_API_KEY\n\n1. Web Search\n\nSearch the web with optional content scraping.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/search\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"query\": \"your search query\",\n    \"engines\": [\"google\", \"bing\", \"duckduckgo\"],\n    \"max_results\": 10,\n    \"scrape_content\": true\n  }'\n\nKey Parameters\nParameter\tType\tDefault\tDescription\nquery\tstring\trequired\tSearch query (1-500 chars)\nengines\tstring[]\t[\"google\",\"bing\",\"duckduckgo\"]\tSearch engines\nmax_results\tinteger\t10\tResults to return (1-100)\nscrape_content\tboolean\ttrue\tExtract full page content\nlanguage\tstring\t\"en\"\tISO 639-1 language code\nResponse\n{\n  \"results\": [\n    {\n      \"title\": \"Page Title\",\n      \"url\": \"https://example.com\",\n      \"snippet\": \"Search result snippet...\",\n      \"scraped_content\": {\n        \"text\": \"Full page content...\",\n        \"word_count\": 2500\n      }\n    }\n  ],\n  \"processing_time_ms\": 1500\n}\n\n2. Agent Search (Tavily-Compatible)\n\nAI-optimized search with optional answer generation.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/agent/search\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"query\": \"What is machine learning?\",\n    \"include_answer\": true,\n    \"max_results\": 5,\n    \"search_depth\": \"basic\"\n  }'\n\nKey Parameters\nParameter\tType\tDefault\tDescription\nquery\tstring\trequired\tSearch query\ninclude_answer\tbool/string\tfalse\tGenerate AI answer (true, \"basic\", \"advanced\", \"production\")\nsearch_depth\tstring\t\"basic\"\tbasic, advanced, fast\nmax_results\tinteger\t5\tResults (1-20)\ninclude_raw_content\tboolean\tfalse\tInclude full page content\ninclude_domains\tstring[]\tnull\tOnly search these domains\nexclude_domains\tstring[]\tnull\tExclude these domains\nResponse\n{\n  \"query\": \"What is machine learning?\",\n  \"answer\": \"Machine learning is a subset of AI...\",\n  \"results\": [\n    {\n      \"title\": \"Machine Learning - Wikipedia\",\n      \"url\": \"https://en.wikipedia.org/wiki/Machine_learning\",\n      \"content\": \"Machine learning is a branch of AI...\",\n      \"score\": 0.95\n    }\n  ],\n  \"response_time\": 1.25\n}\n\n3. Content Extraction\n\nExtract content from specific URLs.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/agent/extract\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"urls\": [\"https://example.com/article\"],\n    \"extract_depth\": \"basic\"\n  }'\n\nResponse\n{\n  \"results\": [\n    {\n      \"url\": \"https://example.com/article\",\n      \"raw_content\": \"Full article text...\",\n      \"failed\": false\n    }\n  ]\n}\n\n4. Deep Research\n\nMulti-source research with AI synthesis.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/agent/research\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"query\": \"Impact of AI on healthcare\",\n    \"depth\": \"deep\",\n    \"max_sources\": 15,\n    \"include_analysis\": true\n  }'\n\nDepth Levels\nDepth\tSources\tUse Case\nquick\t3-5\tFast overview\nstandard\t5-10\tBalanced research\ndeep\t10-20\tThorough analysis\ncomprehensive\t20-30\tExpert-level\nResponse\n{\n  \"executive_summary\": \"AI is transforming healthcare...\",\n  \"key_findings\": [\"AI diagnostics show 95% accuracy...\"],\n  \"sources\": [...],\n  \"model_used\": \"qwq-32b\"\n}\n\n5. Fact Verification\n\nVerify claims against multiple sources.\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/verify/claim\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"claim\": \"GPT-4 was released in March 2023\",\n    \"depth\": \"thorough\"\n  }'\n\nResponse\n{\n  \"verdict\": \"true\",\n  \"confidence\": 95,\n  \"summary\": \"GPT-4 was released March 14, 2023.\",\n  \"supporting_evidence\": [...],\n  \"sources_checked\": 12\n}\n\n\nVerdict values: true, false, partially_true, misleading, unverifiable\n\nPython Examples\nimport httpx\nimport os\n\nAPI_KEY = os.environ[\"UNSEARCH_API_KEY\"]\nBASE_URL = \"https://api.unsearch.dev/api/v1\"\n\nasync def search(query: str, scrape: bool = False):\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            f\"{BASE_URL}/search\",\n            headers={\"X-API-Key\": API_KEY},\n            json={\n                \"query\": query,\n                \"max_results\": 10,\n                \"scrape_content\": scrape\n            }\n        )\n        return response.json()\n\nasync def agent_search(query: str, include_answer: bool = True):\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            f\"{BASE_URL}/agent/search\",\n            headers={\"X-API-Key\": API_KEY},\n            json={\n                \"query\": query,\n                \"include_answer\": include_answer,\n                \"max_results\": 5\n            }\n        )\n        return response.json()\n\nasync def extract_urls(urls: list[str]):\n    async with httpx.AsyncClient() as client:\n        response = await client.post(\n            f\"{BASE_URL}/agent/extract\",\n            headers={\"X-API-Key\": API_KEY},\n            json={\"urls\": urls}\n        )\n        return response.json()\n\nJavaScript Examples\nconst API_KEY = process.env.UNSEARCH_API_KEY;\nconst BASE_URL = \"https://api.unsearch.dev/api/v1\";\n\nasync function search(query, scrapeContent = false) {\n  const response = await fetch(`${BASE_URL}/search`, {\n    method: \"POST\",\n    headers: {\n      \"X-API-Key\": API_KEY,\n      \"Content-Type\": \"application/json\"\n    },\n    body: JSON.stringify({\n      query,\n      max_results: 10,\n      scrape_content: scrapeContent\n    })\n  });\n  return response.json();\n}\n\nasync function agentSearch(query, includeAnswer = true) {\n  const response = await fetch(`${BASE_URL}/agent/search`, {\n    method: \"POST\",\n    headers: {\n      \"X-API-Key\": API_KEY,\n      \"Content-Type\": \"application/json\"\n    },\n    body: JSON.stringify({\n      query,\n      include_answer: includeAnswer,\n      max_results: 5\n    })\n  });\n  return response.json();\n}\n\nRate Limits\nPlan\tQueries/Month\tRate Limit\nFree\t5,000\t10/min\nPro\t25,000\t60/min\nGrowth\t100,000\t200/min\nScale\t500,000\t1,000/min\n\nRate limit headers in response:\n\nX-RateLimit-Remaining: Requests left\nX-RateLimit-Reset: Reset timestamp\nPrivacy Mode\n\nFor sensitive queries, enable zero-retention:\n\ncurl -X POST \"https://api.unsearch.dev/api/v1/search\" \\\n  -H \"X-API-Key: $UNSEARCH_API_KEY\" \\\n  -H \"X-Zero-Retention: true\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"query\": \"sensitive query\"}'\n\nError Handling\nCode\tDescription\n401\tInvalid API key\n429\tRate limited (check Retry-After header)\n422\tValidation error\n500\tServer error\nAdditional Resources\nDocumentation: https://docs.unsearch.dev\nAPI Reference: https://docs.unsearch.dev/api\nSelf-hosting: https://github.com/unsearch-org/unsearch\nGet API Key: https://unsearch.dev"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Rakesh1002/unsearch",
    "publisherUrl": "https://clawhub.ai/Rakesh1002/unsearch",
    "owner": "Rakesh1002",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/unsearch",
    "downloadUrl": "https://openagent3.xyz/downloads/unsearch",
    "agentUrl": "https://openagent3.xyz/skills/unsearch/agent",
    "manifestUrl": "https://openagent3.xyz/skills/unsearch/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/unsearch/agent.md"
  }
}