Maximus' profile on Product Hunt

About

I build PMDesk (https://pmdesk.dev), a Mac app for managing multiple Claude Code and Codex agents, plus project documents, in one window. I work on several client projects and my own products. Over time I moved docs, Q&A, backlog and implementation into AI agents and the command line. One agent per project was easy; many panes in one terminal was not, because I couldn't tell which project a pane was, what it was doing, or whether it was waiting for me. PMDesk is the desk I built to fix that. I write about running AI agents across many projects: subagent token costs, finding client documents without folder-hopping, and how many agents in parallel is too many before review quality drops. Based in Japan. Feedback and questions welcome.

Links

pmdesk

Badges

Tastemaker

Gone streaking

Forums

•

6h ago

Introducing PMDesk: a Mac desk for multiple Claude Code & Codex agents

Hi everyone,

I'm the maker of PMDesk. I work on several client projects plus my own products, and over time I moved almost everything (docs, Q&A, backlog, implementation) into AI agents and the command line. One agent per project was easy. Ten of them was not.

I ran iTerm2 with one screen split into many panes, and I could never tell at a glance which project a pane belonged to, what it was doing, or whether it was waiting for my answer. Reading a client document meant opening Box, finding the file, downloading it, then handing it to the agent.

So I built PMDesk. It's a macOS app for the person directing the agents, not for writing code by hand.

•

9d ago

Running 3-4 Claude Code / Codex sessions at once: what breaks first for you?

I've been running 3-4 Claude Code / Codex sessions at once across different projects, and my biggest time sink isn't the coding. It's losing track of which terminal is blocked on a permission prompt, and which spec each session was supposed to follow. Every time I need the related doc, I have to jump out to another folder, find the file, and then come back to the right terminal.

My current setup is a mix of git worktrees, a markdown file per task, and a lot of tab-checking. It works, but I still miss prompts for 10+ minutes sometimes.

How do you handle it? Do you use tmux, notifications, a task board, or just discipline? And what breaks first when you go from 2 agents to 5?

Disclosure: I'm building a small macOS tool in this space (PMDesk.dev), so I'm genuinely curious what workflows people already trust. Not linking anything here.

p/splithub-io

•

9d ago

What would you let your coding agent A/B test first?

Hi, I m Andrei, the maker of SplitHub. We re launching our coding-agent workflow on October 15.

A coding agent can build three versions of a page quickly. Choosing which version actually helps still needs real traffic and a well-defined conversion goal.

SplitHub gives Claude Code, Cursor and Codex skills, CLI and MCP tools to create experiments, manage them, and read the results. React and Next.js SDKs assign variants locally. The SDK is MIT licensed; self-hosting provides raw counts, while SplitHub Cloud adds statistical analysis and verdicts.

Explore the dashboard without signing in: https://app.splithub.io/demo