Launched this week
AgentPeek
Claude Code and Codex in your Mac notch
144 followers
Claude Code and Codex in your Mac notch
144 followers
Monitor Claude Code and Codex from the Mac notch. Sessions, permissions, token usage, and local dev servers. Session data stays local.
AgentPeek
Also working on running/prompting all inside of the notch - no terminals required.
@brenhuber hey, this is a good idea, is there anyway i can reach out to you??
AgentPeek
@princelex4 Absolutely, thank you very much! - brenhuber.com (X & LinkedIn)
@brenhuber this would be fire, especially if synced w iphone notch
AgentPeek
@sarveshsea 👀
Cool idea! Does AgentPeek work when multiple Claude Code sessions run in parallel? How does the notch UI handle 3-4 concurrent agents?
AgentPeek
@krwdko Yes it does! Any Claude Code and Codex session is tracked from any terminal type (Ghostty, tmux, iTerm, etc.) 👀
Have some specifics on the page - agentpeek.app/docs & agentpeek.app/blog
Notch placement is clever - keeps it out of your workflow without hiding it. Does AgentPeek handle multiple simultaneous Claude Code sessions, or is it scoped to one active session at a time? Running parallel agents is becoming pretty common.
AgentPeek
@christian_knaut Handles multiple simultaneous Claude Code and Codex sessions - no scope!
Having Claude Code visible in the notch is genius ergonomics. As a developer building FinTrackrr, I run Claude Code constantly and alt-tabbing breaks flow. The notch real estate on newer Macs is just wasted space — this is exactly what it should be used for. How are you handling the live output streaming, is it polling or does it use the CLI output directly?
AgentPeek
@asim_saeed1 Appreciate it very much! AgentPeek installs lightweight hooks into Claude Code (~/.claude/settings.json) and Codex (~/.codex/hooks.json) - streams from there.
this is awesome man, I gave you a follow on twitter and git. Love the work, would love to see it utilize tailscale and use my iphone notch for my mac running agents. That would really set this apart.
AgentPeek
@sarveshsea You're awesome! Will look into remote control via iPhone capabilities 👀
Nice idea! I like that it gives visibility into coding agents instead of trying to be another agent. The most useful things for me would be: what’s running, what changed and whether anything is still using tokens.
Do you plan to add history for completed sessions?
AgentPeek
@ihorperkovskyi Thank you! On session completion you can view the full tool call history, diff counts, along with the agent's final in-chat summary.
@brenhuber Nice, that sounds useful. Full tool history + diff counts after completion is probably enough for most review/debugging cases without making the live UI too noisy.
This is really cool! Does it work when coding in an IDE or only in terminal?
AgentPeek
@jordan_paya When using the built-in terminals inside of the IDE, yes! (Cursor, Antigravity, VS Code, etc.)
@brenhuber ahh I see. May I suggest having it pick up sessions running via the Claude code extension running in VS Code or other IDEs? Just something to think about I really love this software!
AgentPeek
@jordan_paya I'll have to look more into that! Currently it utilizes the hook files in .claude and .codex directories to show status, so its native to the terminal CLIs for now.