DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to see every running AI agent on your wallpaper with Infomarchy

Glance at the desktop to see which agents are working, their projects, and their resource use.

  • Top pick
  • Personal productivity
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI

Credentials. The desktop shows recent prompts and session details, so anyone who sees the screen can read what you asked your agents.

Who it is forA developer running Claude Code in several terminals, Codex in another, and a local Ollama model, who loses track of what each one is doing.

The problemKnowing the state of each agent means switching through windows, reading titles, or running monitoring commands by hand.

The outcomeEach running agent shows as a card on the desktop with its project, uptime, pid and a pulsing dot while it is thinking.

What you need first

  • An Omarchy desktop
  • The Infomarchy plugin installed by following the install instructions in the repo README
  • At least one AI agent running locally, such as Claude Code, Codex, Cursor or Ollama
  • Keyboard shortcuts configured as described in the README, for SUPER + I

Steps

  1. Install Infomarchy by following the install instructions in the README.
  2. Open the desktop and look at the Live AI Sessions cards, one per running agent.
  3. Read each card for its project, working directory, uptime, pid and workspace number.
  4. Press SUPER + I to hide the cards and see the plain wallpaper, then press it again to bring them back.
  5. Click a card to focus that agent's terminal.

Prompt for your agent

In the infomarchy repo, follow the README install steps on this Omarchy machine, then list the Live AI Sessions cards visible on the desktop. Expected output: one line per running agent with provider, project and pid. Verify that the count matches the number of agent processes you can see with the process list.

Caveat. The excerpt does not include the install commands, so the first run depends on following the full README, and session data only appears for agents running on this local machine.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for nixfred/infomarchy and "See every running AI agent on your wallpaper"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer