Hasan Toor
@hasantoxr • 437,350 subscribers
AI & Tech Educator • Sharing insights & practical ways to use AI & Tech Tools for you & your daily business
Shorts
Videos
Google just quietly dropped something big for agent builders It's called SAM: Sovereign Agent Mesh A peer-to-peer network where AI agents auto-discover each other, authenticate every packet and call tools across the mesh without a central server Think of it like BitTorrent, but for your agents Right now every agent stack you build is a walled garden. Claude Code talks to its MCPs. Codex talks to its MCPs. If you want agents running on your laptop, your VPS, and your Mac Studio to share tools with each other, you're duct-taping SSH tunnels and REST endpoints together like it's 2015 SAM makes that whole layer disappear You run a sam-node on each machine and the nodes find each other automatically. Every connection is cryptographically identified, so your agents plug in and start calling tools across the whole network The identity is portable too. Same node, same keys, whether it's on GCP, your laptop, or a Raspberry Pi in your closet If you're serious about running agents across multiple devices, get on the testnet this weekend: 1. Install sam-node (binary or Docker) 2. Point it at 3. Connect Claude or Gemini to your local MCP endpoint 4. Watch your agent discover tools running on other people's nodes Still early. Not officially supported by Google. This is where the agent stack is heading. Get on it early Repo:
Hasan Toor41,990 просмотров • 10 дней назад
Holy shit... someone made it work that I can integrate a social media manager inside Claude It's called OmniSocials and it lets Claude draft, schedule, and publish to 10 platforms from a single command. No Hootsuite. No Buffer. No $200/seat pricing. Here's everything you need to know: 👇
Hasan Toor243,246 просмотров • 3 месяцев назад
I'm done paying $500 a month for anti-detect browsers after finding this. It's called CloakBrowser. A stealth Chromium that scores 0.9 on reCAPTCHA v3 (same as a real human) and passes 14 out of 14 bot detection tests. - Auto-resolves Cloudflare Turnstile - Beats FingerprintJS and BrowserScan - TLS fingerprint identical to real Chrome - Drop-in Playwright replacement (one line swap) 100% Opensource. MIT License. What you usually pay for vs CloakBrowser: Bright Data scraping browser → $500+/month Browserless stealth tier → $200+/month Custom anti-detect builds → $10K+ engineering CloakBrowser → pip install, 200MB binary, done. The reason it actually works: Most stealth libraries (playwright-stealth, undetected-chromedriver, puppeteer-extra) inject JavaScript or tweak flags. Every Chrome update breaks them. Antibot systems detect the patches themselves. CloakBrowser patches Chromium's C++ source code in 16 places. Canvas, WebGL, audio fingerprint, fonts, hardware concurrency, GPU vendor strings, WebDriver flag, TLS fingerprint. All compiled into the binary. Detection sites see a real browser because it is a real browser. Stock Playwright scores 0.1 on reCAPTCHA v3. CloakBrowser scores 0.9. Same code. Same API. One import change.
Hasan Toor238,382 просмотров • 3 месяцев назад
This is genuinely impressive. Gauth just dropped Atlas and it might be the end of textbooks. Type any topic like "Silk Road," "how a camera works," "fall of Constantinople" and it builds you a hand-drawn, interactive visual world you can walk through. No more reading walls of text. You explore knowledge like a map. Here's how to use it (step by step): ↓
Hasan Toor231,177 просмотров • 3 месяцев назад
OpenClaw is the best AI agent I've ever used. I run it every single day. But if you asked me to run it on my laptop full-time, I'd say you're making a mistake. OpenClaw is brilliant for accessing your files, reading your apps, and running local AI tasks. But running it on your own machine creates real problems nobody talks about: • Who's keeping it secure when it's exposed to the internet? • What happens when your laptop sleeps or shuts down? • Where are the access controls? • Who's blocking bad bots from hitting your instance? • What if you don't want to spend $800 on a Mac Mini just to run it? That's the main issue with local AI agents: your laptop was never meant to be a server. As far as I know, DigitalOcean is the only platform making OpenClaw cloud deployment this simple. And the security setup is actually impressive: • secret token authentication • bad bot blocking • limited user permissions • Docker containerization All of this configured automatically when you spin up a Droplet. I really don't see any other way forward for people who want OpenClaw running 24/7 without the hardware headaches. By the way, DigitalOcean runs everything in full isolation. Only you can message your OpenClaw instance. Setup takes about 5 minutes. No Mac Mini required. Here's the link to get started: DigitalOcean collaborated with me on this post.
Hasan Toor213,678 просмотров • 4 месяцев назад
A Chinese AI lab just made running Claude Code dirt cheap It's called Step Plan and it routes between their fastest models so you stop burning $20 every time an agent loops. - Works inside Claude Code, Cursor, Cline, Roo Code, Trae - Step 3.5 Flash built for high-frequency agent calls - StepAudio 2.5 ASR for voice pipelines One subscription. Full toolchain.
Hasan Toor114,671 просмотров • 3 месяцев назад
A YC company just shipped the closest thing yet to "type a sentence, get a real company." It's called Naïve. AI employees with their own bank accounts, emails, and credentials. They incorporate LLCs, sign up for tools, and run companies as themselves. No human in the loop. Here's how it works: 👇
Hasan Toor108,667 просмотров • 3 месяцев назад
BREAKING 🚨: Someone finally built an AI that runs your entire business not a chatbot, not a terminal but an actual GUI with live memory and a full team inside. It's called SureThing 2.0 and it's the world's first General AI Agency. Paste a link. One click. It becomes a proactive working employee with a real dashboard.
Hasan Toor133,241 просмотров • 4 месяцев назад
🚨 ElevenLabs just killed every transcription tool on the market. They dropped Scribe v2 Realtime and it's not just another speech-to-text model. This thing processes audio in real-time with zero lag, handles multiple speakers, and actually understands context not just words. Here's how with real examples: Full thread 🧵
Hasan Toor220,656 просмотров • 9 месяцев назад
75% of what you pay Claude for is your agent re-discovering things it already knew yesterday. Graft fixes it with an absurdly simple idea: the agent learns the codebase once, , instead of relearning it every time. it scans the repo, writes it out as linked markdown inside your git, and the agent reads that before touching anything. Here's how:↓
Hasan Toor20,765 просмотров • 29 дней назад
