This week was a good cross-section of where everyone’s at. Some of us are wiring up MCPs inside real companies. Some are building agent harnesses from scratch. Some are just discovering that Webflow can quietly generate full apps. And honestly, that mix is what makes these calls good. Here’s what we covered. * * * 🔌 Rafi: GitHub + Anti-Gravity + MCP at Work Rafi got: - GitHub working - Vercel connected - GitHub connected to Anti-Gravity - And got pulled into an internal “let’s connect MCP to Fathom + Google Drive” conversation at work Which is one of those moments where you realize: > “Oh… I actually know what they’re talking about.” We talked through: - Using Google AI Studio as a shortcut builder - Dropping a PRD directly into AI Studio and letting it build a web app - Using Gmail triggers + Drive automation to process transcripts If you’re in a company environment trying to wire AI into existing workflows, this part’s very practical. * * * 📱 Android App in Two Days? Maybe. Rafi also tried building a simple Android app (a “lock social media until you pray” style blocker). Ran into emulator issues. Burned tokens. Laptop nearly cooked an egg. We talked about: - Why most “2-day app” stories are either glossed over or heavily scaffolded - Using Appwrite / React Native / Flutter-type frameworks instead of raw Android SDK - The difference between web apps and actual app store apps - When it’s worth going native vs. just shipping web-first If you’ve tried to build a “simple” app and discovered it’s not simple, you’ll relate. * * * 🌐 Amadeus: Webflow AI + Gaming Site This was one of the more interesting segments. Amadeus showed a Webflow AI-generated site for a game (Arc Raiders): - Pulling weapon data - Pulling stats - Generating layouts - Creating structured pages with almost no manual input And here’s the thing: It looked good. We talked about: - Webflow possibly wrapping Claude 3.5 - Exporting Astro code - Reverse engineering a PRD from a finished site

This week’s call was a good mix of beginner questions, deep agent architecture, and some real “where is this all going?” conversations. We had five of us on: Wes, Aty, Shawn, Chris, and Gary — and the spectrum of experience in the room actually made the discussion better. Here’s what’s in the video: 🧭 “I’m Not a Developer. Where Do I Start?” Gary’s question was simple and honest: I’ve done some HTML and CSS… but with all this B-Mad, Claude Code, OpenClaw stuff — where do I even start? He’s running VS Code on a Raspberry Pi (which is awesome, by the way), trying to understand the stack without breaking his main machine. We talked about: - Not needing to become a “developer” in the old sense - Starting with outcome definition instead of tools - Keeping early builds simple (MVP mindset) - Avoiding the trap of over-architecting too soon If you’ve felt overwhelmed by: - context windows - local models - agent frameworks - “greenfield vs brownfield” talk You’ll relate to this part. 🧠 Sonnet 4.6, Codex 5.3, and the Shift in Model Power We got into the recent updates: - Sonnet 4.6 improvements - 1M context window options - Codex 5.3 becoming very test-driven - Models increasingly self-checking and structuring output There was a really interesting comparison between Claude and Codex: - Claude tends to “get it working” - Codex tends to enforce tests and longer-term structure That difference matters once your projects get big. 🏗 Chris: Building an OpenClaw Alternative (Local Model Focus) Chris shared that he’s been building his own agent framework — designed to eventually run well on local LLMs. He’s intentionally “skating where the puck is going.” Key themes: - Preparing for local models to get strong enough - Adding guardrails around smaller models - Running into scaling problems as projects grow - The importance of test coverage before things get out of control If you’re building something serious, this part is worth watching.

Today’s call ended up being one of those low-key but important ones. We covered a mix of practical setup stuff and some bigger-picture implications around OpenClaw, open source, and how people are actually starting to use this in real workflows. Here’s what’s in the video: 🧵 Running Multiple OpenClaw Sessions (Without Chaos) Aty walked through how he’s running multiple projects at once using: - tmux for persistent sessions - startup scripts so everything auto-restores on reboot - separate memory/context per project - isolation to prevent session bleed Then we talked about mapping sessions to Discord channels so each project has its own thread — basically treating each agent like its own “room” you can talk to. If you’ve been thinking about: - running multiple agents in parallel - separating business contexts - avoiding token-window collisions This part is worth watching. 🐳 Containers, Kasm, and Business-Specific Agents Wes shared what he’s been doing with: - Docker containers - OpenClaw inside Kasm - shared drives between workspaces - one agent per business Instead of one giant assistant, the idea is: - Ops agent - Marketing agent - Warehouse agent - etc. We also got into a real warehouse example (OCR’ing shipping tickets → matching to POs → auto-updating records). It’s not theoretical — this is the “AI as employee” direction. 💬 Mattermost vs Slack (Open-Source Control) Quick walkthrough of setting up Mattermost as a Slack alternative: - Bot accounts - Token setup - Channel permissions If you want Slack-style workflows without Slack constraints, this part is practical. 🧠 Why OpenClaw Took Off So Fast We had a grounded discussion about: - OpenAI backing OpenClaw - Anthropic’s initial legal response - open-source credibility - autonomy vs corporate structure Not drama — just looking at incentives and what this move signals. 🤖 “Self-Directed” Agent Behavior Aty shared a few observations where OpenClaw: - Adapted after repeated API failures - Changed strategy without explicit instruction - Inferred patterns and adjusted behavior

Everybody's talking about OpenAI buying OpenClaw and hiring Peter Steinberger. Including us. Right now. Come join the discussion and chat live.

Today kicked off something new for the Vibe Coders community: Daily Vibes. This was our very first one, and it set the tone for what these sessions are meant to be—casual, exploratory, and practical. Think of them as short, focused hangs where we test ideas, tools, and workflows in real time instead of over‑polishing presentations. Here’s how it’s going to work going forward: Daily Vibes will happen Monday through Thursday, usually around 10AM CST. They won’t be long—expect anywhere from 10 to 30 minutes depending on the topic and how deep we go. Some days we’ll be testing new tools. Other days we’ll be breaking down workflows, reviewing experiments, or just talking through how we’re actually using AI day‑to‑day as vibe coders. No slides. No sales pitch. Just real work, live. Today’s session was intentionally loose. It was about stress‑testing Claude Desktop's new 'Cowork' feature, poking at Obsidian workflows, and seeing what happens when you give AI real files and real constraints. That’s exactly the spirit of these Daily Vibes. If you caught it live—awesome. If you’re watching the replay, you’re still very much part of it. Show up when you can. Lurk when you want. Jump in when something clicks. This is about building momentum, together, one vibe at a time.