WebClaw

sitemaps don't show you APIs. the APIs live in the JavaScript bundles. new on webclaw: paste any url, get the full hidden API surface in seconds. graphql, REST, websockets, all of it. live on Product Hunt today: producthunt.com/products/webcl…

Repo at: github.com/0xMassi/webclaw

AI agents can onboard themselves. webclaw exposes agent discovery, auth.md, OAuth device flow, MCP, API catalog, OpenAPI, and structured web extraction, so agents can discover, authenticate, scrape, crawl, and extract without a human wiring every step. webclaw.io/auth.md

Repo at: github.com/0xMassi/webclaw

sitemaps don't show you APIs. the APIs live in the JavaScript bundles. new on webclaw: paste any url, get the full hidden API surface in seconds. graphql, REST, websockets, all of it. live on Product Hunt today: producthunt.com/products/webcl…

We are live on ProductHunt! producthunt.com/products/webcl…

Repo at: github.com/0xMassi/webclaw

Your RAG pipeline does not need 1.8MB of docs app HTML. It needs clean markdown. I used webclaw.io on the LangChain quickstart and turned the page into a compact markdown file that is much easier to chunk, embed, or pass to an agent. Example: github.com/0xMassi/webcla…

Repo at: github.com/0xMassi/webclaw

Crawling should feel boring. Give it a starting URL. Set the depth. Let it walk the site and return clean pages. Recorded a quick webclaw dashboard demo: 25 pages scraped in 1,753ms. No browser orchestration. No custom crawler glue. Just structured web context ready to plug into an agent or RAG pipeline. webclaw.io

Repo at: github.com/0xMassi/webclaw

Most scraping demos show one perfect URL. Real workflows use lists. I recorded a quick dashboard demo of webclaw v1/batch scraping: - docs pages - MCP docs - changelogs - pricing pages Multiple URLs in. Clean markdown out. Ready for agents, RAG pipelines, or scripts. webclaw.io

Repo at: github.com/0xMassi/webclaw

Your AI agent should not only read a website. It should understand the brand behind it. webclaw /v1/brand takes any URL and extracts: • colors • fonts • logos • favicons • OG images Perfect for onboarding, enrichment, design audits, and competitor monitoring. Now faster too. webclaw.io

Webclaw hit 1k stars today. A web scraper built for AI agents. clean structured data, fast responses, open source. I didn't expect this when I pushed the first commit. Thank you all.

Just shipped magic link auth to Webclaw. No password. Drop your email, get a code, you're in. Simple login for a tool that's supposed to make your life easier. webclaw.io

hey @thsottiaux, would love a look from the OpenAI OSS program. webclaw: open-source web extraction engine for LLMs and AI agents. Rust, MCP server, AGPL-3. 855 GitHub stars and 1.2k+ users in the first 6 weeks since shipping. github.com/0xMassi/webclaw

35 stars to 1k today. webclaw is a rust scraper built for llm agents, fingerprints chrome over raw http, no headless browser, gets past cloudflare. Open source. if you build with AI, give it a try. github.com/0xMassi/webclaw

LAUNCH50 -> webclaw.io/pricing

shipped the new webclaw dashboard this week. playgrounds that actually run requests, not docs stubs. crawl and research show live progress so you know they're still alive. monitor any URL, get a discord ping when it changes. recent runs you can replay as exact curl, same body you sent. webclaw.io use LAUNCH50 for a 50% off

everyone's wrapping chrome to scrape the web. I shipped a rust binary with a chrome 142 tls fingerprint instead. 5 weeks later: 800 stars on github 1,000 daily active users 0 VC raised 0 paid ads a few hetzner boxes thank you to everyone running webclaw in prod. wild to watch. github.com/0xMassi/webclaw webclaw.io