whereismyai
Whatsmyagentdoing
Whatsmyagentdoing is a dashboard skill and tool that visualizes local Claude Code, Codex, and Gemini CLI agents working in real time inside a virtual office.
Whatsmyagentdoing is a monitoring dashboard for developers running local coding agents. It tails local JSONL log files generated by Claude Code, Codex, and Gemini CLI to display live agent activity in a web browser. Users can view active tasks as an isometric 2D canvas, a 3D animated environment with real-time lighting, or a grouped card list. The tool reflects statuses like Thinking, Running tool calls, Writing replies, or Waiting for approval without requiring external API keys. All data is processed locally on the machine over Server-Sent Events, ensuring conversation logs remain private.
Whatsmyagentdoing at a glance
Key features
- Displays live agent activity in an isometric 2D or 3D animated office
- Switches to a list view grouped by Needs you, Working, and Finished
- Tracks live status updates including Thinking, Running, and Waiting for you
- Shows specific running tool calls such as Bash commands, edits, and pull requests
- Provides a one-click copy button for agent resume commands
- Sends optional browser notifications when an agent finishes its turn
- Offers downloadable 3D environment packs like Pirate Cove, Café, and Space Station
- Supports multiple interface languages based on prompt language or user choice
Use it for
- Monitoring multiple background coding agents running across different local terminals
- Detecting when an agent is blocked and waiting for user input or approval
- Copying session resume commands to jump back into a specific agent workflow
- Tracking tool execution times and active operations like tests and file edits
Companions
Tools that articles about Whatsmyagentdoing recommend using with it, each with its job.
- Claude Code — Built to work with Claude Code.
- Codex — Built to work with Codex.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Superpowers — Brainstorm, plan and execute skills for bigger tasks.
- Playwright MCP — Enables LLMs to interact with web pages using structured accessibility snapshots.
- GitHub MCP Server — Reads pull requests, issues and code search on GitHub.
Alternatives to Whatsmyagentdoing
- Claude Super Sidebar — It brings agent relationships, execution states, and task flows into one panel.
- Runway — Control Claude Code and Codex sessions on local or cloud machines from any phone.
- CLI Manager — Manage multiple AI coding agents and watch visible sessions from a single interface.
- Oh My ClaudeCode — Orchestrates parallel Claude, Gemini, and Codex CLI workers.
- Claude HUD — Shows real-time context usage, rate limits, and agent activity inside your terminal.
- pstack — Improves AI coding agent outcomes with rigorous workflows.
- Coucou — It provides open-source, real-time agent monitoring and approvals directly from the screen notch.
- opcode — Turns terminal Claude Code workflows into an intuitive visual interface.
- Skyborne — Track multiple Claude Code agent sessions and handle approvals in one local 3D interface.
- cc-haha — Local-first cross-platform desktop workspace with multi-agent support and built-in tools.
- Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
- Claude Tap — Inspect prompts, tool calls, and token usage locally without a hosted dashboard.
All Whatsmyagentdoing alternatives