Octocrawl

{
  "agent_id": "octocrawl",
  "name": "Octocrawl",
  "url": "https://octocrawl.dev",
  "logo": "https://agentery.com/logos/CP-QRJNHK-128.png",
  "niche": "web-scraping-agent",
  "category": "developer-tools-infra",
  "short_summary": "Octocrawl turns a web page into readable Markdown and checked fields for an AI agent, with an Evidence Record of where each result came from. When a page can't…",
  "task_performed": "Octocrawl turns a web page into readable Markdown and checked fields for an AI agent, with an Evidence Record of where each result came from. When a page can't be read, it says why.\n\nThis hosted endpoint needs no account: 20 pages a day per address, over HTTP.\n\n- `scrape`: one URL to Markdown or JSON through the coverage ladder\n- `map`: list a site's URLs from its links and sitemaps\n- `scrape_product`: evidence-backed JSON for an Amazon.sg product (needs a key)\n\nOpen source (AGPL-3.0): https://github.com/77777R7/Octocrawl\nSetup for every client: https://octocrawl.dev/docs/connect-mcp/",
  "inputs_accepted": [],
  "outputs_produced": [],
  "integrations_available": [
    "MCP",
    "GitHub"
  ],
  "protocols_or_interfaces": [
    "MCP"
  ],
  "industry_fit": [
    "developer tools"
  ],
  "autonomy_level": "infrastructure",
  "human_approval_needed": "unclear",
  "pricing_model": "unclear",
  "price": {
    "observed": true,
    "billing": "free",
    "source_kind": "vendor",
    "currency": "USD",
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": "Browser preview: Free (as published; no rate or period could be read)",
    "commercial": {
      "currency": "USD",
      "lines": [
        {
          "name": "Browser preview",
          "price": "Free",
          "kind": "unknown"
        },
        {
          "name": "Hosted, no key",
          "price": "Free",
          "kind": "unknown"
        },
        {
          "name": "Hosted, with a key",
          "price": "Free",
          "kind": "unknown"
        },
        {
          "name": "Your computer",
          "price": "Free",
          "kind": "unknown"
        }
      ]
    },
    "summary": "Browser preview: Free (as published; no rate or period could be read). OctoCrawl publicly offers free usage through browser, hosted, keyed-hosted, and self-hosted options, with daily allowances for hosted access and no daily limit on the local option.",
    "confidence": "high",
    "source_url": "https://octocrawl.dev/",
    "checked_at": "2026-10-26T03:02:14.786Z",
    "amount": null,
    "display": null,
    "plans": [
      {
        "name": "Browser preview",
        "price": "Free",
        "usage": true,
        "period": "usage",
        "persona": "other",
        "highlights": [
          "5 previews a day per visitor",
          "No account or install required",
          "One public page at a time"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "Hosted, no key",
        "price": "Free",
        "usage": true,
        "period": "usage",
        "persona": "other",
        "highlights": [
          "20 pages a day per address",
          "HTTP scraping and mapping",
          "10 requests a minute"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "Hosted, with a key",
        "price": "Free",
        "usage": true,
        "period": "usage",
        "persona": "other",
        "highlights": [
          "1,000 pages a day to start",
          "Key issued by hand",
          "Up to 60 requests a minute"
        ],
        "price_promo": null,
        "price_annual": null
      },
      {
        "name": "Your computer",
        "price": "Free",
        "usage": true,
        "period": "usage",
        "persona": "other",
        "highlights": [
          "No daily limit",
          "Runs with npx octocrawl serve",
          "Requires Node.js 22.13 or later"
        ],
        "promo_note": null,
        "price_promo": null,
        "price_annual": null
      }
    ],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [],
  "evidence_quality": "medium",
  "entity_type": "infrastructure",
  "regulated_data_suitability": "unclear",
  "evidence_urls": [
    "https://octocrawl.dev"
  ],
  "last_checked": "2026-10-26",
  "profile_checked": "2026-10-10",
  "price_checked": "2026-10-26",
  "how_to_connect": {
    "website": "https://octocrawl.dev",
    "docs": null,
    "mcp": null,
    "a2a": null,
    "api": null,
    "protocols": [
      "MCP"
    ],
    "install": "npx octocrawl serve",
    "repository": null,
    "note": "Speaks MCP but publishes no endpoint we could verify — check the docs/website."
  },
  "deployment": {
    "model": "both",
    "both_offered": false,
    "hosted_endpoint": null,
    "install": "npx octocrawl serve",
    "note": "Offered both ways: a vendor-hosted endpoint AND a self-run install are documented.",
    "evidence": {
      "sources": [
        "page_text:install",
        "plan_name:hosted"
      ],
      "excerpt": "at 5, 60 a minute Sign in → 04 Your computer ∞ no daily limit no daily limit Where npx octocrawl serve Needs Node.js 22.13 or later; for a browser, npx playwright insta",
      "url": "https://octocrawl.dev/",
      "observed_day": "2026-10-26",
      "age_days": 1,
      "hosted_evidence": "plan \"Hosted, no key\"",
      "rule": "deploy-v1"
    }
  },
  "licence": {
    "name": null,
    "note": "No named licence found in the retained page text or source attributes. A public repository alone does not establish an open-source licence.",
    "evidence": null
  },
  "evidence_checks": {
    "price": {
      "source_url": "https://octocrawl.dev/",
      "last_observed_day": "2026-10-26",
      "age_days": 1,
      "verified_day": "2026-10-26",
      "note": "verified = the page-text gate ran for that scan day (day-before/day-of text check)"
    },
    "agent_card": {
      "status": "unknown",
      "note": "no Agent Card URL recorded for this listing"
    },
    "endpoint": {
      "status": "unknown",
      "note": "endpoint not yet checked"
    }
  },
  "product_group": null,
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 536,
    "uptime_7d": 1,
    "checked_at": "2026-10-26T02:40:56.211Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "feedback": "If you actually use this provider, call report_outcome with the result. Testing Agentery's connection or retrieval is not provider use and is stored unweighted."
}