Monitoring for your coding agents

For each session, AgentPeek shows the state (executing, thinking, waiting, or idle, plus an attention flag) and the detail its source exposes: current activity, files touched, commands, diffs, todos, tool calls, prompts, and answers. Agents that report subagents show them under their parent. The same layout covers all twenty-six agents, from Claude Code to Command Code.

The primary surface is the Mac notch: always present, glanceable, expanding on demand. The Agent Board floats a kanban of every session for the wide view, widgets pin todos, transcripts, or usage anywhere on any display, and menu bar mode carries usage gauges to notchless setups. Same live state, whichever surface fits your desk.

A dashboard you can only read still makes you switch to a terminal to act. From AgentPeek you allow or deny permissions, answer questions, approve plans, and send the next prompt into a resumable session, with replies streaming into the session card. Monitoring and response sit on one surface, so you answer without leaving the notch.

AgentPeek is a desktop app, not a hosted observability service. It reads what your agents already keep on your Mac. During ordinary monitoring, AgentPeek does not upload transcripts, diffs, prompts, or usage numbers. The desktop app has no AgentPeek account, product analytics, or telemetry. The public website uses Cloudflare Web Analytics, which does not run inside the app.