{"id":49618549,"url":"https://github.com/us/openclaw-plugin-crw","last_synced_at":"2026-05-05T00:07:47.495Z","repository":{"id":347575957,"uuid":"1194507750","full_name":"us/openclaw-plugin-crw","owner":"us","description":"CRW web scraping plugin for OpenClaw — scrape, crawl, and map websites","archived":false,"fork":false,"pushed_at":"2026-04-04T17:38:05.000Z","size":74,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-04T20:22:17.082Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/us.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-28T13:02:42.000Z","updated_at":"2026-04-04T17:37:55.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/us/openclaw-plugin-crw","commit_stats":null,"previous_names":["us/openclaw-plugin-crw"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/us/openclaw-plugin-crw","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/us%2Fopenclaw-plugin-crw","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/us%2Fopenclaw-plugin-crw/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/us%2Fopenclaw-plugin-crw/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/us%2Fopenclaw-plugin-crw/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/us","download_url":"https://codeload.github.com/us/openclaw-plugin-crw/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/us%2Fopenclaw-plugin-crw/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32629759,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-04T10:08:07.713Z","status":"ssl_error","status_checked_at":"2026-05-04T10:08:02.005Z","response_time":58,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-05-05T00:07:43.592Z","updated_at":"2026-05-05T00:07:47.475Z","avatar_url":"https://github.com/us.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# openclaw-plugin-crw\n\n[![npm version](https://img.shields.io/npm/v/openclaw-plugin-crw)](https://www.npmjs.com/package/openclaw-plugin-crw)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n\n[CRW](https://github.com/us/crw) web scraping plugin for [OpenClaw](https://github.com/openclaw/openclaw). Gives your AI agents the ability to scrape, crawl, and map websites.\n\n## Installation\n\n```bash\nopenclaw plugins install openclaw-plugin-crw\n```\n\n## Setup — Pick One\n\n### Option A: Cloud ([fastcrw.com](https://fastcrw.com)) — Quickest Start\n\nNo server to install. [Sign up at fastcrw.com](https://fastcrw.com) and get **500 free credits** to start scraping:\n\n```json\n{\n  \"plugins\": {\n    \"crw\": {\n      \"apiKey\": \"crw_live_...\"\n    }\n  }\n}\n```\n\nThat's it — cloud is the default. Your agents can now scrape, crawl, and map any website.\n\n### Option B: Self-hosted with binary (free, no limits)\n\nSingle binary, ~15 MB download, ~6 MB idle RAM. No Docker needed.\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/us/crw/main/install.sh | sh\ncrw  # starts on http://localhost:3000\n```\n\n```json\n{\n  \"plugins\": {\n    \"crw\": {\n      \"apiUrl\": \"http://localhost:3000\"\n    }\n  }\n}\n```\n\n### Option C: Self-hosted with Docker\n\n```bash\ndocker run -d -p 3000:3000 ghcr.io/us/crw:latest\n```\n\n```json\n{\n  \"plugins\": {\n    \"crw\": {\n      \"apiUrl\": \"http://localhost:3000\"\n    }\n  }\n}\n```\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `crw_scrape` | Scrape a single URL and get clean markdown |\n| `crw_crawl` | BFS crawl a website, collect content from multiple pages |\n| `crw_map` | Discover all URLs on a website via sitemap + link traversal |\n| `crw_search` | Search the web for results with titles, URLs, and descriptions; optionally scrape full content with `scrape: true` (cloud-only) |\n\n## How It Works\n\nOnce installed and configured, your OpenClaw agents use the CRW tools automatically:\n\n### Scrape a page\n\n**User (via WhatsApp/Telegram/Discord):** \"Summarize this article: https://example.com/blog/post\"\n\n**Agent uses `crw_scrape`** → gets clean markdown → summarizes → responds.\n\n### Crawl an entire site\n\n**User:** \"Research everything on docs.example.com\"\n\n**Agent uses `crw_crawl`** → discovers and scrapes all pages → synthesizes findings → responds.\n\n### Discover site structure\n\n**User:** \"What pages does example.com have?\"\n\n**Agent uses `crw_map`** → returns all discovered URLs via sitemap + link traversal.\n\n## Example: URL Scraper Bot\n\nA simple OpenClaw agent that scrapes any URL users send:\n\n1. User sends a URL via WhatsApp/Telegram\n2. Agent detects the URL and calls `crw_scrape`\n3. CRW fetches the page (using [fastcrw.com](https://fastcrw.com) cloud or your local instance)\n4. Agent receives clean markdown — no HTML noise, no nav/footer\n5. Agent summarizes and replies\n\nWith fastcrw.com, no infrastructure needed — just plug in your API key and go.\n\n## Compared to Firecrawl Plugin\n\n| Feature | CRW Plugin | Firecrawl Plugin |\n|---------|-----------|-----------------|\n| Cloud option | [fastcrw.com](https://fastcrw.com) | firecrawl.dev |\n| Self-hosted | Yes (single binary, ~6 MB) | Complex (5+ containers) |\n| API key required | No (self-hosted) | Yes (always) |\n| Idle RAM | ~6 MB | ~500 MB+ |\n| Avg latency | 833ms | 4,600ms |\n| Cost (self-hosted) | $0 | $0 but heavy infra |\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fus%2Fopenclaw-plugin-crw","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fus%2Fopenclaw-plugin-crw","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fus%2Fopenclaw-plugin-crw/lists"}