🚨BREAKING: In partnership with Stripe, Hermes Agent now supports a full suite of Stripe skills

Your agent can buy things, pay per-call APIs, and provision its own SaaS, with configurable safety limits on every action.

🚨Right after the BIGGEST IPO in history comes this: Elon Musk's SpaceX $SPCX to acquire AI coding startup Cursor for $60,000,000,000🤯

🚨CURSOR JUST LAUNCHED ORIGIN

A purpose-built Git platform that treats
AI agents as first-class users, complete with S3-backed infinite replicas and built-in handling for merge conflicts that agents create during parallel work.✴️

"Don't look at the agentic era,
experience it up close"

⬇️Join the waitlist⬇️
https://cursor.com/origin

🥳400 subscribers!!
For some they are not many, for me it is already a good goal🔖
Thanks to each of you🫂

Stay tuned that my partner and I are about to launch something awesome😉

🚨JUST IN: CLAUDE CODE NOW SUPPORTS ARTIFACTS 😒

Starting today, Claude Code can capture work progress as an artifact, which turn Claude Code's work into live, shareable visual pages— including PR walkthroughs, system explainers, dashboards, and release checklists—that update themselves as your session works.

⬇️Read more⬇️
https://claude.com/blog/artifacts-in-claude-code

🚨GLM 5.2 ranks 1st overall on Design Arena’s single-turn, HTML Web Design (Non-Agentic) evaluation, 5 places higher than its predecessor GLM-5.1.

To do so, it beat Claude Fable 5, Opus 4.6, and Opus 4.7, a model line that has held the top spots for months on their leaderboards and won more head-to-head matchups than any other model they track.

💙MCP Market Hub is building a cleaner way to manage Agent Skills and MCP tools in one place. +165.000 skills🤯

✴️It brings together:
- version control for skills,
- automatic syncing across agents,
- a shared MCP catalog,
- team-friendly toolkits,
- visibility into tool calls, errors, and latency.

In short: less chaos, more structure.

If you work with Claude Code, Claude Desktop, Codex, or other MCP clients, this looks like a useful place to create, version, and distribute skills and tools without handling everything manually😉

⬇️Start here⬇️
https://mcpmarket.com/hub

🚨JUST IN: 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🧠

Before there were the 10 commandments. Now the Slate of Hermes🪨

⬇️Read more⬇️
https://hermes-agent.nousresearch.com/docs/getting-started/quickstart

GLM 5.2 IS A HIT🚀

Been out for 3 days and it's already 6th on Opencode leaderboard👑

Is dominating benchmarks for autonomous coding and long-time horizon tasks🔝

GLM 5.2 is available to configure in Claude Code, OpenClaw, and Cline. At a cost of about 1/6 of GPT-5.5 with comparable performance for standalone coding😣

🚨BREAKING: NSA Director General Joshua Rudd says Mythos broke into “almost all” classified systems in hours.

A week after Washington forced Anthropic to disable its most powerful models, the likely reason is sharpening. According to reports Senator Mark Warner told a hearing that the NSA and Cyber Command chief said the firm's Mythos model penetrated almost all of the agency's classified systems within hours🤯

🚨BREAKING: a tiny lab in Tokyo just built a model that matches the performance of Fable and Mythos🤯

Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.

Their ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.

⬇️Try it⬇️
sakana.ai/fugu

📲A complete reverse engineering suite that runs entirely on Android — no PC, no ADB, and no desktop tools required.

📌Features
• APK extraction and analysis
• Java decompilation (multiple decompilers)
• Native ELF/.so binary analysis
• Control Flow Graph (CFG) visualization
• Flutter & IL2CPP support
• Radare2 integration
• Fully on-device workflow

☁️https://github.com/UltraSina/androidReverse

🚨JUST IN: THE NATIONAL CYBER SECURITY CENTER LAUNCHES AN ALARM

The AI shift in cyber risk: why leaders must act now.
😊Five Eyes cyber security agencies urge organisations to act on rapidly transforming cyber risk.

AI is not a future consideration – it is already here.

👨‍💻It lowers barriers for malicious actors and increases the speed and complexity of attacks, shrinking the window between vulnerability discovery and exploitation ever more quickly☠️
At the same time, AI offers powerful tools to strengthen defence🔒

⬇️Read more⬇️
https://www.ncsc.gov.uk/news/the-ai-shift-in-cyber-risk-why-leaders-must-act-now

⚡️NEW IN HERMES AGENT: /learn — turn what you already know into a reusable skill

No more writing SKILL.md by hand. Point the agent at a source, it builds the skill for you.

📄What it accepts:
→ Local SDK or doc folder
→ Online documentation pages
→ A workflow you just walked the agent through
→ Pasted notes or a described procedure

↪️Examples:
• /learn the REST client in ~/projects/acme-sdk, focus on auth + pagination
• /learn https://docs.example.com/api/quickstart
• /learn how I just deployed the staging server

🔤The agent ingests the material with the tools it already has, then writes a skill following house standards — 60-char description cap, standard section order, Hermes tool structure, no invented commands.

📞Works identically in CLI, messaging gateway, TUI, and dashboard.
Dashboard → Skills page → "Learn a skill" button: directory field, URL field, free-text box. Composes a /learn request and runs it in chat.

No separate ingestion engine. Same skill_manage write gate as everything else. Less manual work. More leverage.

🕷A web scraping python library that uses LLM and direct graph logic to create scraping pipelines for websites and local documents (XML, HTML, JSON, Markdown, etc.)

Just say which information you want to extract and the library will do it for you!

↪️It offers seamless integration with popular frameworks and tools to enhance your scraping capabilities.
👩‍💻Whether you're building with Python or Node.js, using LLM frameworks, or working with no-code platforms, we've got you covered with our comprehensive integration options

You can also use with Hermes😉

🔗https://scrapegraphai.com

🌐GOOGLE JUST UPGRADED GOOGLE FINANCE

Three major features launched today:

🛰AI-POWERED PORTFOLIO TRACKING

Drop in screenshots, upload CSVs or PDFs, or just describe your holdings and Google Finance builds your portfolio automatically. Once set up you can ask questions like "what sectors are underrepresented in my portfolio?" or "how does my fixed income allocation impact my long-term growth potential?"

👤PERSONALIZED MARKET BRIEFINGS ON A SCHEDULE

Describe a task like "send me a daily pre-market briefing analyzing significant overnight moves across major cryptocurrencies" and Google Finance runs it automatically on your schedule. Notifications push through the Google app.

👍NEW GOOGLE FINANCE APP FOR ANDROID

Real-time data, live financial news feed, AI research tool, and AI-powered "key moments" that explain why a stock moved. iOS app coming later this year.

"Investing will become smarter and smarter🧠"

This is an aggregator that gives you API access to 136+ LLMs at zero cost🆓

⌨️What you get access to:
- Minimax M3, Kimi K2.6, GLM 5.1, DeepSeek V4 Pro, Mistral, 136+ models total, one API key for all of them

😣Who this is for:
- testing ideas before committing to paid APIs
- building AI agents on a budget
- experimenting with workflows across different models
- prototyping side projects without burning money

Not a trial. Not a freemium trap. Just free API access to 136+ models⌨️

🔗https://freellm.net/

Guys if you didn't know this site, you don't know where the AI world really happens🤖

👩‍💻Papers With Code is the insider hub — every new model, every breakthrough, every benchmark, all curated daily from arXiv and Hugging Face with the code right next to the paper. Filter by trending, newest, or most cited↗️

📄Browse between: Language Modeling, Reasoning, Coding Agents, World Models, Robotics, OCR, Image Generation — whatever you're into.

This is the playground of the researchers shaping what's next. Get in early, learn fast, build smarter☕️

🔗https://paperswithcode.co/