Ingest documentation, crawl entire sites, and convert any HTML into clean, token-efficient Markdown. API, CLI, and browser extensions for your RAG pipelines and AI agents.
curl -X POST https://api.unweb.info/api/convert/url \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url": "https://example.com/article"}'
All processing happens in-memory over HTTPS. Nothing is ever stored, logged, or analyzed. Your content stays yours.
UnWeb doesn't just strip tags — it understands content structure and extracts only what matters.
Built from the ground up for developer-first AI workflows.
Automatically detects main content using semantic HTML, content scoring, and paragraph density analysis. Strips nav, ads, footers, and sidebars.
RESTful endpoints for paste, upload, and URL fetch. Drop into LangChain, LlamaIndex, or any custom agent pipeline in minutes.
Your HTML and Markdown are processed in memory and returned — never stored on disk or sent to third parties. Fully encrypted over HTTPS.
Strict CommonMark for universal compatibility. Predictable parsing, no GFM ambiguity. Clean output every time.
Paste raw HTML, upload files, or fetch directly from URLs. Batch process entire CMS exports or wiki dumps.
No infrastructure to manage. Call api.unweb.info and get Markdown back. Free tier included — no credit card required.
UnWeb processes your content in memory and returns the result. Your HTML and Markdown are never stored or sent to third parties. Every request is encrypted over HTTPS. Content goes in, Markdown comes out, and that's it.
From solo projects to enterprise agent systems, UnWeb fits anywhere clean content is needed.
Convert documentation dumps, wiki exports, and help center pages into clean chunks for your RAG pipeline. Works with LlamaIndex, LangChain, and any vector store.
Give your AI agents clean markdown from any URL. No more parsing HTML in your agent loops. One API call, structured output.
Strip navigation chrome, footers, and ads from documentation pages. Feed your LLM only the content that matters — save 80%+ on tokens.
Standardize web content into a consistent markdown format across all your agents. No more per-site parsing logic.
Create a free account, grab an API key, and start converting.
Create a free account at app.unweb.info and generate an API key from the dashboard.
Call the API with your HTML — paste it, upload a file, or pass a URL. Use cURL, Python, JS, Go, or the CLI.
Receive clean, semantic Markdown instantly. Feed it to your LLM, vector DB, or agent chain.
Pay for what you use. Different operations cost different credits. Paid plans include overage billing so your pipelines never stop.
Everything you need to integrate — pick your language, your platform, or your workflow.
Full API coverage with sync and async clients. Python 3.9+.
TypeScript-first, zero runtime dependencies. Node 18+.
Create a free account, grab your API key, and start converting HTML to clean Markdown in under a minute. No credit card required.
