iSlayer

I See some competition here. 🥴 @TheMobileBot @checkouters @kochclub_xyz

@discord just limited my account again for “fraud”. Last time they closed our entire server for the exact same bullshit and zero proof. This account is clean. Never joined shady/NSFW servers, never did anything sketchy, been using it normally for years. Still no explanation. No real support answer. Just radio silence. This shit is getting really annoying.

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

🧵 Tired of your AI being BLIND to the live web? Messy HTML. Bot blocks. Sky-high token costs. Your RAG is stale, your agents hallucinate, and competitive intel takes hours of manual checking.

Summarize, anything, in seconds. The web scraper your AI agent actually deserves. webclaw.io

What if your AI agent could actually scrape the web? webclaw.io

Scraping data in 2026? You’ve almost certainly hit the Cloudflare wall: sudden 403 errors or fake HTML challenge pages. Cloudflare now protects over 20% of all websites. Silent failures and $500/month proxy bills aren't real solutions. Here is what actually works. 🧵 1/8

First week of Webclaw since its opensource release, overall: - 220+ Github stars - 700+ clones - Webclaw's custom TLS has been released Thank you all for appreciating our efforts, more to come. Stay tuned. github.com/0xMassi/webclaw

Sunday building...

New in Webclaw: /search Designed to search and extract anything from web directly in your agent. Provide any real time data to your LLM.

my pleasure

New in Webclaw: /scrape Designed to extract structured data from web pages not just raw HTML, but clean, parsed content ready for programmatic use. Provide any real time data to your LLM.

🤖

Introducing Webclaw, releasing open source this week.

The 403 problem Here's what happens when you try to scrape anything in 2026. You install one of those popular scraping tools. You pass it a URL. You wait. 403 Forbidden. Or worse, you get back HTML that's just a Cloudflare challenge page, and the library says "here's your content!" like it did something useful. So you look at the docs. "For pages behind anti-bot protection, enable our premium proxy network." Ah. Cool. So the free tier is basically a fetch() wrapper that breaks on any real website. Got it. Or you try one of those "ethical" crawlers that respects robots.txt. Which, fine in principle. But when you're building an AI agent that needs to read a pricing page to compare options for a user, you're not a search engine. You're not indexing the web. You just need to read a page. The same page any human can read by clicking a link. These tools treat every URL like you're about to DDoS it. Meanwhile your browser opens the same page in 200ms, no questions asked. apply at: webclaw.io/waitlist

stik v0.6.0 unified command palette. codemirror 6 editor. slash commands with custom templates. interactive markdown tables. apple notes import. → stik.ink

day 9. release 9. stik v0.5.0: formatting toolbar, font zoom, root-level notes, cleaner image export. 100+ stars 1000+ downloads free. open source. → stik.ink → github.com/0xMassi/stik_a…

stik — instant thought capture for macOS. one shortcut. post-it appears. type. close. back to work. plain markdown files. on-device AI search. 8MB. no cloud. no account. MIT open source. brew install --cask stik github.com/0xMassi/stik_a… stik.ink