Foolery – a web UI for orchestrating Claude Code agents on top of Beads
Replaces tmux chaos with visual agent orchestration—dependency graphs, live monitoring, verification queue.
Live view of your AI agents at work.
Tamagotchi-style agent monitor, but approval workflows already exist in Cursor and Cline.
Developers using autonomous coding agents (Cursor, Claude, Cline, VS Code)
Cursor Agent Monitor · Cline Dashboard · GitHub Copilot real-time feedback
Replaces tmux chaos with visual agent orchestration—dependency graphs, live monitoring, verification queue.
Localhost-only agent monitor with approval gate, but lacks proof of cross-tool compatibility.
Detects AI agents reading secrets without wrapping your workflow unlike Little Snitch.
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.
Kanban for AI agents, but no orchestration—you still drive the decisions.
No-build-step frontend with SQLite persistence for CLI agent monitoring.