{"id":13911033,"url":"https://github.com/supermemoryai/markdowner","last_synced_at":"2025-05-16T08:03:20.669Z","repository":{"id":238960813,"uuid":"798096430","full_name":"supermemoryai/markdowner","owner":"supermemoryai","description":"A fast tool to convert any website into LLM-ready markdown data. Built by https://supermemory.ai","archived":false,"fork":false,"pushed_at":"2024-07-21T04:03:59.000Z","size":32,"stargazers_count":1356,"open_issues_count":11,"forks_count":107,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-05-15T15:58:02.022Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://md.dhr.wtf","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/supermemoryai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"code_of_conduct.md","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}},"created_at":"2024-05-09T04:55:20.000Z","updated_at":"2025-05-15T11:06:44.000Z","dependencies_parsed_at":"2024-05-09T06:31:21.084Z","dependency_job_id":"ef96ab08-8d0c-487d-a472-71295ff74e6e","html_url":"https://github.com/supermemoryai/markdowner","commit_stats":null,"previous_names":["dhravya/markdowner","supermemoryai/markdowner"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supermemoryai%2Fmarkdowner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supermemoryai%2Fmarkdowner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supermemoryai%2Fmarkdowner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/supermemoryai%2Fmarkdowner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/supermemoryai","download_url":"https://codeload.github.com/supermemoryai/markdowner/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254493381,"owners_count":22080126,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":"2024-08-07T00:01:55.120Z","updated_at":"2025-05-16T08:03:20.637Z","avatar_url":"https://github.com/supermemoryai.png","language":"TypeScript","funding_links":[],"categories":["TypeScript","others","网络服务"],"sub_categories":["网络爬虫"],"readme":"# Markdowner ⚡📝\n\nA fast tool to convert any website into LLM-ready markdown data.\n\n## 👀 Why?\n\nI'm building an AI app called Supermemory - https://git.new/memory. Where users can store website content in the app and then query it using AI. One thing I noticed was - when data is structured and predictable (in markdown format), the LLM responses are _much_ better.\n\nThere are other solutions available for this - https://r.jina.ai, https://firecrawl.dev, etc. But they are either:\n\n- too expensive / proprietary\n- or too limited.\n- very difficult to deploy\n\nHere's a quote from my friend [@nexxeln](https://github.com/nexxeln)\n![what users think](https://i.dhr.wtf/r/Clipboard_May_9,_2024_at_12.35 AM.png)\n\nSo naturally, we fix it ourselves ⚡\n\n## Features 🚀\n\n- Convert any website into markdown\n- LLM Filtering\n- Detailed markdown mode\n- Auto Crawler (without sitemap!)\n- Text and JSON responses\n- Easy to self-host\n- ... All that and more, for FREE!\n\n## Usage\n\nTo use the API, just make GET a request to https://md.dhr.wtf\n\nUsage example:\n\n```\n$ curl 'https://md.dhr.wtf/?url=https://example.com'\n```\n\n##### _REQUIRED PARAMETERS_\n\nurl (string) -\u003e The website URL to convert into markdown.\n\n##### _OPTIONAL PARAMETERS_\n\n`enableDetailedResponse` (boolean: false) -\u003e Toggle for detailed response with full HTML content.\n`crawlSubpages` (boolean: false) -\u003e Crawl and return markdown for up to 10 subpages.\n`llmFilter` (boolean: false) -\u003e Filter out unnecessary information using LLM.\n\n##### _Response Types_\n\nAdd `Content-Type: text/plain` in headers for plain text response.\nAdd `Content-Type: application/json` in headers for JSON response.\n\n## Tech\n\nUnder the hood, Markdowner utilises Cloudflare's [Browser rendering](https://developers.cloudflare.com/browser-rendering/) and [Durable objects](https://developers.cloudflare.com/durable-objects/) to spin up browser instances and then convert it to markdown using Turndown.\n\n![Architecture diagram](https://i.dhr.wtf/r/Clipboard_May_9,_2024_at_12.25 AM.png)\n\n## Self hosting\n\nYou can easily self host this project. To use the browser rendering and Durable Objects, you need the [Workers paid plan](https://developers.cloudflare.com/workers-ai/platform/pricing/)\n\n1. Clone the repo and download dependencies\n\n```\ngit clone https://github.com/dhravya/markdowner\nnpm i\n```\n\n2. Run this command:\n   ```\n   npx wrangler kv:namespace create md_cache\n   ```\n3. Open Wrangler.toml and change the IDs accordingly\n4. Run `npm run deploy`\n5. That's it 👍\n\n## Support\n\nSupport me by simply starring this repository! ⭐\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsupermemoryai%2Fmarkdowner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsupermemoryai%2Fmarkdowner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsupermemoryai%2Fmarkdowner/lists"}