Find your people.
See how they work.
A look inside the tools, agents and everyday workflows of people building with AI.
Top 20 setups for “coding from my phone”
Stevey Brown
@steveybrown…Codex is now my primary agent harness, with Claude Code as my second coding agent. Depending on how much I max out my plans on a weekly basis. I run both in auto mode inside Herdr with varying levels of effort depending on the task at…
1,819 viewsRyan Mazzolini
@rmazzolini…Fable for UI planning and adversarial reviews, and remote access from laptop and phone. What I use AI for I work with coding agents to investigate problems, compare approaches, and build software. I like making complex things simpler. I…
993 viewskbarendrecht
@kbarendrecht…hand that back to the agent. My setup Claude Code on Opus 5: my only coding agent. orchestrator (disclaimer: it's my own tool) used at work and at home. A Rust daemon plus a small web app that runs several Claude Code sessions over one…
522 viewsShubham Naik
@4shubShubham Naik @4shub Engineer at Letta coordinating persistent cloud coding agents through chat.letta.com, with Zed and connected engineering tools for implementation, debugging, and review. Shubham Naik’s AI setup What I build I’m an…
328 viewsInterestingSoup
@interesting-soup…The stack is self-hosted on Linux via Coolify. AI is both my coding partner and a live feature inside the product. The WhatsApp bot (Hasaan) The squad's primary AI interface. Messages prefixed with ai on PSN or @bot on WhatsApp to Hasaan…
241 viewsioloro
@ioloroioloro @ioloro Solo developer shipping iOS/macOS apps and a geospatial computer-vision pipeline, run through Claude Code plus a fleet of local and cloud agents.
345 viewsKuyawa
@kuyawaKuyawa @kuyawa Programmer in love with DeepSeek, check my page for detailed info, it will change your life What I build Apps, agents, harnesses, bots Agents & harnesses DeepSeek Harness clone in Swift Apps Everything Models deepseek-flash…
561 views프론트엔드 개발자
@member-1d18544c프론트엔드 개발자 @member-1d18544c Claude로 계획하고, Orca 안의 Claude Code로 구현하고, Antigravity로 코드를 읽는 웹·모바일 프론트엔드 개발자의 셋업. 무엇을 만드나 웹과 모바일 앱의 프론트엔드를 만듭니다. AI는 작업 계획, 구현, 코드 품질 점검에 씁니다. 일하는 방식 작업 계획은 Claude 앱 에서 먼저 정리합니다. 다른 관점이 필요하면 ChatGPT에도 물어봅니다. 구현은…
26 viewskatspaugh
@katspaugh…mobile app for psychotherapists. What I use AI for All of the coding: web frontend and backend, mobile and Mac OS development. Code reviews. Various hardware projects with RPi and ESP-32. Jailbreaking and home brewing on devices like…
445 viewso-f
@o-f…anything writes. Agents & harnesses opencode-zen (current): Everyday coding agent for the Omarchy tree; OpenCode with Big Pickle . Grok Build TUI (current): Default Omarchy coding agent; Buckeroo for Omarchy Q&A. grok.com (current): Writes…
242 viewsTaylor Houston
@tttaylorrr…Houston @tttaylorrr I build Overclock, a flat-rate inference API for coding agents. Solo founder, self-funded, whole stack: the proxy layer, billing, and the product itself. Most of my day is agent work. Not "AI writes my code" demos —…
223 viewsNick Yeager
@nick-yeager…with Codex as my daily driver. How I work My core setup is Codex for coding, Herdr for managing agent sessions, and Rulemetric baked into the agent workflow. Rulemetric's hooks connect it to the session, where relevant instruction and…
87 viewsJoshua
@joshua-pham…a focused project thread, give the work a clear boundary, and let coding agents inspect evidence, use tools, and return reviewable results across local or remote environments. Obsidian : This is my durable, human-readable source of truth…
656 viewsbluehotdog
@bluehotdog…AI works with the interface that actually renders, not just guesses from source code. Agents & harnesses Frontman (current): An open-source, browser-based coding agent. Select an element, describe a change, and it edits the real source…
568 viewsKW Na
@member-2c840fe7KW Na @member-2c840fe7 Kotlin/Spring Boot 백엔드 개발자. IntelliJ + Claude Code, 레포에 규칙·리뷰 에이전트·훅을 넣어 컨벤션을 하네스로 강제한다. 내가 하는 일 Kotlin · Spring Boot 기반 멀티모듈 백엔드 모노레포(API, 인증 BFF, 배치)를 개발한다. AI는 설계 논의, 구현, 마이그레이션 작성, 커밋 전 리뷰에 쓰고, 최종 판단과 코드 확인은 내가…
19 views99991
@9999199991 @99991 Running DeepSeek in my own sandboxed harness What I use AI for CUDA kernel optimization Other verifiable tasks where the agent can check its work My setup I built my own harness for maximum control over what my agent does:…
228 viewsJimmy T
@xeno…same-chat implementation What I use AI for Product work in a coding agent: first implementation, small follow-ups, and a second look before I accept a change. Agents & harnesses Cursor Agent (current): Daily coding harness. I stay in the…
728 viewsWes Sander
@ucsandman…wrote preflight / ship / launch / announce (current): A product goes from finished code to public through the same gates every time, including an SEO floor and search-console registration in the same change. wes-voice (current): Anything I…
1,626 viewsDru Ibarra
@druwerdDru Ibarra @druwerd Backend engineer on a multi-service platform. Claude Code does ticket-to-draft-PR work through personal skills, with guardrail hooks, parallel subagents and my own runtime checks before merge.
902 viewsGareth Price
@gareth…workflow that compiles a weekly digest of arXiv papers in our field from RSS sources. It scores each paper (1000+ per week), a review pipeline pulls full text for ~10% of the ones of most interest and it publishes a digest each week to…
1,613 viewsCurious about someone’s AI setup? Ask them to share it.
Add their @mentions in X.