Ema

Self-taught devs don't need companies to validate them. They need the right tools. I built JARVIS for myself. Now I'm building it for all of us. This is what it does. 🧵

42 minutes is wild. The bottleneck shifts from coding to orchestrating — managing multiple agents, reviewing outputs, dispatching work across machines. I built JARVIS for exactly this: a mission control app for AI dev workflows. Tauri (Rust + Svelte), open source: github.com/emawritz/share…

People are seriously underestimating this mobile app dev workflow I built a mobile app in about 42 minutes: - 8 minutes to generate screens - and another 34 minutes to turn it into a working MVP app Step 1: I had the idea, but I needed a clean UI design fast for the app. I asked grok to generate a base prompt & then plugged it directly into my own mobile app design tool (Appthetics). I tweaked the brand identity and the screens were ready then I grabbed the export prompt and moved on. Step 2: I pasted the entire prompt into Anything AI Builder and gave it one instruction: “Build this health app without changing the UI. Make sure to handle every edge case.” The AI builder took about 14 minutes to generate a simple working MVP, and another 20 minutes something to add a RevenueCat paywall. And the simple working MVP was ready in 42 minutes. Holy moly

The open source alternatives moving fast. browser-use for web, coding agents for dev — but orchestrating all of them across machines is the missing piece. I built JARVIS for this: Tauri desktop app (Rust + Svelte) that monitors and dispatches AI agent tasks across machines. github.com/emawritz/share…

Holy shit. OpenAI just launched Operator and charged $200/month for it. Someone built the exact same thing: open source, free, runs locally. It's called browser-use. 78,000 GitHub stars. Your AI agent can now: - Click buttons - Fill out forms - Scrape any website - Apply to jobs - Book flights - Manage your inbox All in plain Python. No cloud. No subscription. Your data never leaves your machine. 3 lines of code to start: agent = Agent( task="Find the cheapest flight to Tokyo next week", llm=ChatOpenAI(model="gpt-4o") ) That's it. It runs in your browser and doe

Containerized dev environments are the right foundation. The next layer is orchestrating agents across those environments. I built JARVIS — a Tauri desktop app that manages Claude Code agents across multiple machines (local + remote via SSH), with real-time monitoring and task dispatch. Open source: github.com/emawritz/share…

someone just dockerized an entire AI coding workstation and it's kind of insane one docker compose up and you get: → Claude Code with a browser UI → Gemini, Codex, Cursor, TaskMaster CLIs → Playwright + Chromium, pre-configured → 50+ dev tools (pandas, ffmpeg, prisma, gh...) no config. no debugging "why won't chromium run in docker" uses your existing Claude Max/Pro subscription github.com/CoderLuii/Holy…

@RoundtableSpace OSS coding agents are heating up. What's missing is orchestration across machines. Built JARVIS for this — Tauri desktop app that dispatches tasks via SSH/Tailscale and monitors sessions in real-time. github.com/emawritz/share…

GOOSE IS A FREE OPEN SOURCE AI CODING AGENT BUILT BY BLOCK THAT WORKS WITH ANY LLM YOU WANT. No lock in, no monthly fee, and it can read, edit, run, debug, and execute code across your machine like a real agent.

@akshay_pachaar Incredible breakdown. Multi-agent orchestration got me hooked — built JARVIS around it. Tauri mission control for Claude Code across machines, task dispatch, pipeline viz. OSS: github.com/emawritz/share…

Claude Code Unpacked! Visual walkthrough of the entire 500k-line leaked codebase. What happens when you type a message: - the agent loop - 50+ tools - multi-agent orchestration - unreleased features Want to understand the internals or build your own agent harness? start here:

@_vmlops Great resource. Once you learn multi-agent patterns you need orchestration across machines. Built JARVIS for this — monitors Claude Code sessions, dispatches tasks via SSH. Open source: github.com/emawritz/share…

This free GitHub repo teaches Claude Code better than Anthropic’s own docs Learn Claude Code walks through 12 sessions covering: • Agent loops • Planning agents • Persistent tasks • Multi-agent teams Link - github.com/shareAI-lab/le… Anthropic explains what it is This repo shows how to build with it

@arafatkatze Hard agree. Built JARVIS for this — Tauri app (Rust + Svelte) that monitors Claude Code sessions across machines, dispatches tasks, tracks pipelines. Multi-agent needs mission control UX. github.com/emawritz/share…

Calling it now, This form factor of multi agent orchestration will overtake every other agentic UX in the next six months. Doesn’t matter if it’s coding agent, product management agent or something else. Every multi agent flow of frontier models currently suffers from 2 main problems 1. Inference bound: Most of the time you are just waiting on inference while the agent rips on code in the background and that can take 8-10 minutes fairly regularly so the wait time very expensive productivity wise. 2. Take Isolation: you will work on the same mutating “source code ” with multiple agents in parallel each of which are inference bound and so eventually you will run into countless merge conflicts The kanban board solves for both of them by giving you the ability to act as an engineer manager for your IC individual agents, watching them cleanly with a clear headline level out look of every parallel agent. It works seamlessly with any coding agent whether it’s cline or codex or Claude code. To me this is a mental model shift that takes 10 minutes, you use the same coding agents like you always used before this but it will fundamentally morph your coding agent experience. Try out kanban and let us know what you think. npm i -g cline Is all you need.

This is exactly the direction I've been obsessing over. I built JARVIS — a Tauri desktop app (Rust + Svelte) that orchestrates Claude Code agents across multiple machines via SSH/Tailscale. Real-time session monitoring, task dispatch to GPU rigs, pipeline visualization. Just open-sourced it: github.com/emawritz/share…

🚨 Claude Code just got superpowers. Someone built a multi-agent orchestration layer on top of Claude Code that gives it 5 execution modes, 32 specialized agents, and 3-5x faster output. Zero learning curve. No new tools. No new subscriptions. Just Claude Code running like it was always meant to. It's called oh-my-claudecode. Here's what's inside: → Autopilot mode: fully autonomous execution, just describe the task and walk away → Ultrapilot mode: spins up parallel agents and runs 3-5x faster on multi-component builds → Swarm mode: coordinates multiple agents working independently toward the same goal → Pipeline mode: sequential chains for multi-stage processing tasks → Ecomode: token-efficient execution that saves 30-50% on costs without sacrificing quality Here's what actually makes this different: 32 specialized agents for architecture, research, design, testing, and data science. Smart model routing uses Haiku for simple tasks and Opus for complex reasoning automatically. You never think about which model to use. The system decides. One magic keyword and everything changes: → Type "autopilot" and it builds the whole thing autonomously → Type "ralph" and it goes into persistence mode, won't stop until the job is verified complete → Type "eco" and it switches to budget mode → Type "plan" and it runs a planning interview before touching a single file The wildest part? It auto-resumes your Claude Code sessions when rate limits reset. No babysitting. No manually restarting. Just continuous execution. 3.6K GitHub stars. 100% Open Source. Link in comments.

I just open-sourced JARVIS. A native desktop app to orchestrate AI coding agents across multiple machines — from a single dashboard. What it does: → Real-time monitoring of Claude Code sessions → Task dispatch to any machine via SSH/Tailscale → Git workflows, pipelines, branch management → Full session timeline and analytics Built with Tauri 2 + Rust + Svelte 5. No cloud. No subscriptions. Runs on your local network. MIT License. Star it, fork it, ship with it. github.com/emawritz/share…

Update: JARVIS is now open source. The full codebase is live on GitHub — Tauri 2, Rust backend, Svelte 5 frontend. MIT license. Orchestrate AI coding agents across multiple machines from one dashboard. No cloud needed. Star it, fork it, break it, improve it. github.com/emawritz/share…

Self-taught devs don't need companies to validate them. They need the right tools. I built JARVIS for myself. Now I'm building it for all of us. This is what it does. 🧵

@RoFerreiraDev Ollama en un vps!

@emaacejas97 Lo de supervisión con IA suena re interesante. Con qué modelo estás laburando?

Mi psicólogo maneja todo su consultorio desde WhatsApp y Excel. Turnos, cobros, notas, recordatorios, informes para obras sociales.Todo manual. Un día le pregunté cuánto tiempo le tomaba. "Todo el domingo", me dijo. Un día entero de su fin de semana que no es terapia. Ahí entendí el problema. Así que lo estoy construyendo. Un sistema que hace todo eso solo para que el profesional se enfoque en lo que importa: sus pacientes.

Pronto subo capturas del panel completo. Agenda, videollamadas, facturación, copilot IA, todo en acción.

Red de derivación, historia clínica digital, supervisión IA. Todo en una sola plataforma. Hecho por un dev argentino que escuchó el problema de primera mano.

Agenda inteligente con vista día, semana y mes. Drag & drop para mover turnos. Recordatorios automáticos por WhatsApp. El paciente confirma con un click.