Agent FM – local, open-source radio for Claude Code and Codex agents
Turns agent terminal output into ambient radio—Global Mix monitors all sessions at once.
Desktop 'Paperclip' Companion for Claude Code & Codex
It wires Claude Code hooks and a passive tailer for Codex session files into a tiny floating pet window that reports agent states (Thinking, Working, Waiting, Done, Error) and live context/token counts. The local status.json approach keeps data on your machine and the sticker packs give it actual charm, but it's a narrowly useful desktop companion — multi-session or dashboard support would make it materially more powerful.
Developers who run AI coding agents (Claude Code, Codex) from the terminal and want lightweight, local visibility without staring at logs
I built a small desktop companion that monitors CLI AI coding agents so you don’t have to stare at the terminal during long tasks.
It shows when the agent is done, needs input, and the current token/context usage (useful to know when it’s about to compact). It’s fully local + free + open source: https://github.com/fredruss/agent-paperclip
It supports Claude Code via hooks and Codex CLI by watching local session files. Default sticker pack is a small Clippy nod (no affiliation, Microsoft please don't sue me).
Next on the to-do list: multi-session visibility.
Would love feedback / issues / stars.
Turns agent terminal output into ambient radio—Global Mix monitors all sessions at once.
No-build-step frontend with SQLite persistence for CLI agent monitoring.
Notch pet that lives in your MacBook notch while tracking Claude token usage.
Think of an RTS game UI for your coding LLMs: spawn Claude or Codex agents, assign tasks, and watch them produce diffs and file edits in real time on a 3D or 2D canvas. The repo bundles practical developer features — built-in file explorer with git diffs, conversation history, permission controls and a command palette — which turns the spectacle into a usable workflow. It’s delightful and ambitious, but gated by the need for Claude/Codex CLIs and local infra, so expect it to appeal mostly to experimenters rather than plug-and-play users.
GUI wrapper around CLI agents with task protocol, but Cursor and Continue already coordinate agents.
Like top for AI agents: tracks token costs across 6 coding agents, 100% offline.