Get the weekly radar
One short email with the freshest products, every week.
AgentPeek monitors 26 coding agents from your Mac's notch — sessions, prompts, spend, all local.
Grounded in available product and source data
Six terminal windows for six coding agents is a normal Tuesday for some developers, and none of them show what's actually happening at a glance. AgentPeek exists to monitor those coding agents from a Mac's notch instead, turning that scattered setup into one centralized panel.
Live session monitoring is the core of it: project, state, and pending action for each agent show up in a Kanban board grouped by status, with floating chat windows for individual sessions so a developer can view a transcript and reply to an agent without switching to its original terminal. Activity tracking goes deeper than a status light — transcripts, tool calls, diffs, cost, and token usage are all visible, alongside permission-prompt handling and running totals for spend and usage-limit windows across every connected agent.
Developer-workflow tools sit right next to the monitoring: a local dev server can be opened, copied, or stopped directly from AgentPeek, and an agent's skills, plugins, config, and logs are reachable from the same interface, alongside saved shell commands and a terminal workspace launcher. Coverage is broad rather than limited to one or two popular tools — 26 named agents are supported, including Claude Code, Codex, Cursor, GitHub Copilot, Devin, Aider, and Goose among others, installed via each agent's supported hooks or plugins.
Data handling is specific rather than a vague promise: the site states AgentPeek keeps all data locally on the Mac during ordinary monitoring and does not upload code, prompts, transcripts, or diffs, with network requests limited to license checks, updates, and a few named agent-specific connections. Pricing is a single pay-once purchase scaled by machine count rather than a subscription, with every tier including unlimited sessions and no account requirement, backed by a free 3-day trial. What's worth noting for anyone relying on it heavily: the app is built and maintained solo by one developer, so support responsiveness and long-term update cadence are worth watching rather than assuming a larger team is behind it.
A short list — license checks, app updates, and a few named agent-specific connections like Kimi usage tracking — rather than anything from the sessions being monitored, since ordinary monitoring data itself never leaves the Mac.
As many as are running — the app supports 26 named agents including Claude Code, Cursor, Devin, and GitHub Copilot, and unlimited sessions are included on every pricing tier.
No — every tier is stated to require no account and includes no app analytics, which fits the broader local-data-only approach the app is built around.
Only Apple silicon Macs running macOS 14 or later — it's a native Swift app, with full notch-integrated display on notch-equipped Macs and a menu bar mode for machines without one.
A solo developer, Bren Huber, per the site — worth keeping in mind for anyone evaluating long-term support and update cadence versus a larger dedicated team.
These 2 comments were collected from the discovery source. ProductVisit does not host replies in Release A.
Hey Product Hunt 👋 I'm Bren, the solo dev behind AgentPeek. I basically live in Claude Code and Codex now. The problem: too much time spent babysitting them. Manually checking tabs, usage, servers, whether anything's actually finished, all while I'm just trying to watch some YouTube. IT DOESN'T HAVE TO BE LIKE THIS! So I built AgentPeek. It puts every agent's live status right in your MacBook notch. One glance tells you what's running, what needs you, and what just finished. Lovely! The part I'm most excited about is how little it asks of you: - Live status in the notch. Running, waiting on you, or done, at a glance. - Approve or deny permission prompts straight from the notch, without leaving the app you're in. - Watch each tool call as it happens (reads, edits, commands), each with its own glyph. - Zero setup. It reads the hooks Claude Code and Codex already fire, so you just open it and it works. And that's just the start. There are dozens of small quality-of-life touches baked in too, the kind of thing I added because it bugged me as a dev and now I can't work without them. I built this for my own workflow first, so I'd genuinely love your feedback. QUESTION: what do you need out of this app? I'm shipping constantly and focused on practical, time-saving stuff, so tell me what would actually help. Thanks for checking it out 🙏 p.s. I post what I'm building on X at @brenhubr if you want to follow along and connect. Show more
1 source upvotesThe notch is a great spot for this, I usually have three or four Claude Code sessions going and lose track of which one is blocked waiting on me. Does it show which repo each session belongs to when you have a bunch running? congrats on shipping
1 source upvotes