Serg Eroshenkov

Coding with AI? Kick off your next project with one command: npx start-vibe-project It scaffolds your docs, architecture, and specs from minute zero. github.com/itechmeat/star… 🧵 1/6 #VibeCoding

I just claimed my .agent domain and joined the .agent community! get yours now and help shape the future of autonomous agents #0MCDHXGF" target="_blank" rel="nofollow noopener">agentcommunity.org/join#0MCDHXGF @agentcommunity_

We did this last year. It worked. Now we are doing it again. I will be leading the next ZK & Privacy Bootcamp - bridging the gap between theory and real applications 🤗 Applications below 👇 Want to sponsor and help shape what they focus on? Reach out - my DMs are open 📩

opencode 1.3.0 will no longer autoload the claude max plugin we did our best to convince anthropic to support developer choice but they sent lawyers it's your right to access services however you wish but it is also their right to block whoever they want we can't maintain an official plugin so it's been removed from github and marked deprecated on npm appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

Amazon just published a blog on x402! It provided full reference architectures for integrating the protocol into AWS infrastructure for financial services TLDR of what it covered: - x402 revives HTTP’s 402 “Payment Required” status code as a programmable payment rail for autonomous AI agents, developed by Coinbase - The flow: agent requests a resource, gets a 402 response with a payment spec, pays via USDC micropayment on-chain, resubmits with receipt; sub-2-second settlement at roughly $0.0001 per transaction - No subscriptions, no API key management, no vendor contracts; agents pay per use on demand - Every transaction is recorded on-chain, giving a full audit trail by design - AWS published three reference implementations: 1) AgentCore + CloudFront + x402 (agent side) 2) CloudFront + Lambda@Edge + WAF (merchant/provider side), and; 3) a general guide for monetizing any HTTP app via x402 - FSI use cases highlighted: trading agents accessing real-time data feeds, compliance agents pulling sanctions lists, credit decisioning agents querying bureau data; all per-query instead of fixed subscriptions - McKinsey projects agentic commerce will mediate $3 trillion to $5 trillion of global commerce by 2030 Why this is notable: - This is AWS legitimizing x402 as enterprise infrastructure - They’re shipping reference architectures, sample repos, and integration guides that map directly onto Bedrock AgentCore (their managed agent stack) and CloudFront (their CDN/edge layer) - AWS is effectively telling FSI institutions: this is how your agents will pay for things. - The fact that the blog sits under their Financial Services Industries vertical, cites McKinsey’s $3-5T projection, and frames x402 alongside compliance and audit requirements, signals that AWS sees this as a production-grade payments primitive, as opposed to a niche protocol That’s a massive distribution and credibility unlock for x402 adoption - follow @KhalaResearch we have a full report dropping this week I’ll link the article below

Still doubting if you need a proper methodology when writing code with AI? Spoiler: You definitely do. I highly recommend this excellent practical guide on Spec-Driven Development to get you started: todorovic.dev/blog/spec-driv…

This dropped right as I'm starting a new @livekit Agents project. To hit the ground running, I created a dedicated coding skill that already includes Agents UI: github.com/itechmeat/llm-… Let's build 🚀

Выложил свой опенсорсный аналог эвернота с блэкджеком и маркдауном. Если кому-то будет интересна идея, поддержите звездочкой github.com/denisfl/inbox Могу лично провести демо. Работы там еще полно, что-то криво работает. Но лучше набрать панамку фидбека, чем хранить в полке.

Z.ai Startup Program is NOW OPEN. What you can get: ·Free API credits ·Priority rate limits ·Exclusive Community ·Early API Access Who we're looking for: ·AI-native startups ·Agent builders ·SaaS founders integrating LLM infra ·Global teams building for real-world scale If you're building something that matters, don't wait!! Apply now: startup.z.ai Questions? Details? Follow & DM @ZaiforStartups

TranslateGemma 4B by @GoogleDeepMind now runs 100% in your browser on WebGPU with Transformers.js v4. 55 languages. No server. No data leaks. Works offline. A 4B parameter translation powerhouse, right in your browser. Try the demo 👇

Got 🦞 @PicoClaw working on an old Android via Termux + GLM-4.7 by @Zai_org. Built from source for ARM64, used @claude_code on the same phone to set everything up. Now it just runs as a Telegram bot. Pretty cool for a $0 setup.

@cyntro_py Great case. Inspired by this, I gave Claude a link to a service that didn't work for me and asked for a refund. It read the dashboard, pulled the invoice details, wrote a formal letter, then replied to the support bot on its own. I just watched 🍿

I had money stuck with a crypto card provider. Months of support tickets led to nothing. Claude Code sent one email threatening regulatory action which resolved it in 2 days without any actions from my side. Today, there's zero marginal cost to fight back. Every grievance gets filed by customers.

@kkomelin @Alibaba_Qwen @openclaw I haven't used it for coding yet, only inside OpenClaw

@techmeat @Alibaba_Qwen @openclaw How good is the model for coding?

The new @Alibaba_Qwen coding plan for qwen3.5-plus is live! Had to wrestle with the setup a bit, but it's up and running in my @OpenClaw environment. 🦞 Skip the headache and grab my working config here: gist.github.com/itechmeat/609c…

@Alibaba_Qwen Vibe coding? @Alibaba_Qwen what the model was used here? :)

@Alibaba_Qwen It's really cool! But it's really a quest to get this subscription.

🚀 Qwen Coding Plan is now live on Alibaba Cloud Model Studio! ✨ What you get: • 🔥 Latest Qwen3.5-Plus models • 💡 Fixed monthly subscription: from ~$10/mo (Lite) or ~$50/mo (Pro) • 📦 Up to 90K requests/month for AI-powered coding • 🔌 Works with Claude Code, Qwen Code, Cline, Cursor & more • 🔥 Get 50% OFF on Lite & Pro plans with our launch coupon! 🔗 Get started:  alibabacloud.com/help/en/model-…

Finding product market fit as a solo founder.

A lot of people quote tweeted this as 1 year anniversary of vibe coding. Some retrospective - I've had a Twitter account for 17 years now (omg) and I still can't predict my tweet engagement basically at all. This was a shower of thoughts throwaway tweet that I just fired off without thinking but somehow it minted a fitting name at the right moment for something that a lot of people were feeling at the same time, so here we are: vibe coding is now mentioned on my Wikipedia as a major memetic "contribution" and even its article is longer. lol The one thing I'd add is that at the time, LLM capability was low enough that you'd mostly use vibe coding for fun throwaway projects, demos and explorations. It was good fun and it almost worked. Today (1 year later), programming via LLM agents is increasingly becoming a default workflow for professionals, except with more oversight and scrutiny. The goal is to claim the leverage from the use of agents but without any compromise on the quality of the software. Many people have tried to come up with a better name for this to differentiate it from vibe coding, personally my current favorite "agentic engineering": - "agentic" because the new default is that you are not writing the code directly 99% of the time, you are orchestrating agents who do and acting as oversight. - "engineering" to emphasize that there is an art & science and expertise to it. It's something you can learn and become better at, with its own depth of a different kind. In 2026, we're likely to see continued improvements on both the model layer and the new agent layer. I feel excited about the product of the two and another year of progress.

This is a super relevant initiative @embirico @code, @claudeai, @opencode, @kilocode