Ouroboros DeFi "O-De" @ObFinancial

decided to write the full start-to-finish guide to running Hermes Agent 24/7: copy-paste commands, every one tested on real hardware, on a cheap VPS or a Mac Mini. if you have been meaning to start, this is your on-ramp. I will be more than happy to help if you still struggle on a specific part. please let me know!

witcheer @witcheer

2 days ago

x.com/i/article/2069…

5 34 232 112K 756

x.com/i/article/2064…

@OuncesApp @Grantemayer @DarioCpx Not to mention there was just one bidder

The Alchemy plugin for Claude Code is live. One install and Claude can query 100+ chains and run your Alchemy account. Create apps, manage keys, all from the terminal. "What's the price of ETH?" → real answer, live data, in your terminal. Open source, OAuth sign-in, 160+ tools.

Trading

Xona Agent @xona_agent

2 days ago

XONA spotted under Consumer Application / Commerce on the 2026 Agentic Finance Landscape by @HouseofChimera. More eyes on agentic commerce.

5 9 37 2K 0

You can try Workers for free here: → aiworkers.so

🚨 BREAKING The new Steam Machine will go with a local Claude preinstalled > Sonnet 4.6 model: $1,049 > Opus 4.8 model: $1,349 Gabe Newell said: we want everyone to have access to local LLMs and pay no subscriptions hit a like for a legend

Milady @onchainmilady

5 days ago

x.com/i/article/2067…

6 23 154 548K 594

@saiharinathredd @DarioCpx How does it offset ? the flood of closing this volume of shorts would push prices up

@HormuzLetter Make Iran Export Again

STOP TYPING MANUAL PROMPTS INTO CLAUDE. In a new 26-minute breakdown, this Anthropic engineer shares a massive shift in how we should be thinking about AI: "Don’t prompt models. Build systems that prompt themselves." The problem? 95% of builders are completely missing the core architecture to make this happen. Here is where they go wrong: ❌ They forget to establish a continuous memory file. ❌ They rely on one massive prompt instead of modular sub-agents. ❌ They fail to build stop conditions, leading to infinite loops and bloated API bills. If you are still typing out repetitive tasks by hand, you are driving a sports car in first gear. Watch the video below, and then read @Saboo_Shubham_'s ace article on "Loop Engineering for Product Managers" You'll learn how to transition from one-off tasks to building self-improving AI systems 👀↓

Shubham Saboo @Saboo_Shubham_

3 days ago

x.com/i/article/2068…

20 81 460 128K 1K

🇺🇸🇮🇷🇵🇰 The feelings of shock and disappointment on the face of Pakistan's Prime Minister, after he was informed by the Iranian delegation they are leaving after Trump threatened them.

Sean Penn is set to direct a new feature film about the January 6th riots, with Bradley Cooper cast as a police officer. Penn’s directed two films that feature my favorite actor Jack Nicholson: The Crossing Guard & The Pledge. Both are quality films that demonstrate Penn’s skills as a director. He’s more than qualified to hold the keys to a film.

10 GITHUB REPOS THAT SCRAPE THE ENTIRE INTERNET FOR YOU Bookmark every single one. Each one pulls clean data off any website on earth, the kind of access companies sell behind a sales call and a contract. 1. github.com/mendableai/fir… Point it at any website and it crawls every page, renders the JavaScript, and hands back clean structured data an AI can read instantly. It crossed 130K stars and landed in GitHub's top 100 repos. The scraping backbone half the AI startups quietly run on, open for anyone. 2. github.com/unclecode/craw… The #1 trending crawler on GitHub. Turns any site into clean, LLM-ready markdown, faster than the paid services and with no API key, no account, no per-page fee. A dev built it in days after getting fed up paying $16 for a gated scraper. 51K stars. Apache 2.0. 3. github.com/browser-use/br… An AI agent that drives a real browser like a human, clicking, scrolling, logging in, filling forms, and pulling data off sites it has never seen before. Two ETH Zurich researchers built it and it hit 95K stars in about a year. The thing that scrapes pages no simple crawler can reach. MIT. 4. github.com/apify/crawlee The full professional scraping framework, with rotating proxies, automatic retries, browser fingerprint spoofing, and queue management, all the machinery that keeps you from getting blocked. The exact stack scraping companies charge thousands to operate, handed to you for free. 5. github.com/scrapy/scrapy The original industrial-strength scraper that has quietly powered data teams for over a decade. Crawl millions of pages, extract anything, export it clean. Battle-tested at a scale most paid tools never reach, and free the entire time. 6. github.com/microsoft/mark… Microsoft's own tool that converts any file or web page, PDFs, Office docs, HTML, images, into clean markdown an AI can actually use. The messy-data-to-clean-data step companies build whole pipelines around, open-sourced by Microsoft itself. 7. github.com/D4Vinci/Scrapl… A stealth scraper built to stay invisible, adapting automatically when a site changes its layout and slipping past the bot detection that stops everything else. The cat-and-mouse layer that anti-scraping vendors sell as a premium feature, free and open. 8. github.com/Genymobile/scr… Mirror and control any Android phone from your computer to pull data and automate apps that have no website at all. The bridge into mobile-only platforms that most scrapers can't touch. 130K+ stars. Apache 2.0. 9. github.com/alirezamika/au… Show it one example of what you want and it figures out the pattern and scrapes the rest of the site automatically. No selectors, no code to maintain. The "just get me this data" button, in a few lines of Python. 10. github.com/lwthiker/curl-… A version of curl that perfectly mimics a real browser's fingerprint, so the requests sneaking past every defense look exactly like a human with Chrome open. The lowest-level trick the expensive scraping APIs are quietly built on top of. Companies sell this access for $2,000 a month. The source code is right here.

keyboard_arrow_left Previous keyboard_arrow_right Next

@djohnson195305 @peterbakernyt Iran insurance authorities will 😆

GLM 5.2 might be the “ChatGPT moment” for local AI The moment many of us see the value in local models GLM 5.2 isn’t perfect, but it’s really good 1M token context window so it holds an entire codebase at once. Top open model on coding right now. MIT licensed with zero restrictions. And it runs on your own machine through Ollama or LM Studio. When you're using it, it kinda feels like Opus 4.8. I honestly can't believe how good it is. 2027 is probably the year of local AI.

Mat Velloso @matvelloso

6 days ago

All day using GLM 5.2. Didn't miss much. First open model that passes the bar as a daily driver. Things are not going to be the same. Damn, now I want to buy some serious hardware.

150 308 6K 1.9M 2K

Hermes Bible is live. A community-built place to search Hermes Agent docs and real workflows in seconds. 169 docs pages. 24 community flows. Instant ⌘K search. Unofficial. Community-built. Not affiliated with @NousResearch I built this because the Hermes community is moving fast, and the best workflows should not get buried in X Articles, Discord, or random posts. Read the docs. Study the flows. Submit your own. If your flow gets added, I’ll link back to your X profile. hermesbible.com

x.com/i/article/2067…

x.com/i/trending/206…

hermes agent just shipped a setup mode called blank slate and it's the most i've liked a feature decision in a while. instead of an agent that comes with everything bolted on, you start with almost nothing, a provider, a model, file operations, and a terminal, and you opt into the rest yourself. that's the whole agent to start. then you add the tools and skills you actually use, one at a time, and nothing else is sitting in your config or eating your context. the flow is stupid simple, install with one line: curl -fsSL hermes-agent.nousresearch.com/install.sh | bash then run hermes setup, pick blank slate, and a couple minutes later you've got a working agent carrying exactly what you told it to carry, nothing more. hermes itself runs on 18 dependencies and the agent loop is a single file you can actually read, so there's not much hiding in there to begin with. i keep coming back to this because it's the opposite of how most tools think. the default everywhere is more, more skills, more integrations, more surface. blank slate bets that you know what your agent needs better than a defaults menu does, and on hardware you own that bet is almost always right, you're the one who has to live with whatever's loaded. if you've been meaning to run an agent well and the all in one setups felt like too much, this is the one to start on. one model, one terminal, build up from there. the install's one line anon, go see for yourself.

Nous Research @NousResearch

4 days ago

Hermes Agent has a new Blank Slate setup mode. The default Quick/Full setup modes work great for most, but if you would rather build your agent from the ground up you can now start with just a provider, model, file operations, and terminal, then manually add in anything else.

190 170 3K 319K 948

The Top 10 Most Popular Films on Letterboxd This Week 👽